arXiv subjects

Adam Block

Publications and source records attributed to Adam Block.

At least 19 recordsLinked to original sources

arXiv2026

Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback

Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training. A central puzzle is that, while in theory offline IL can be horizon-free and optimal, in practice online methods such as on-policy distillation often outperform offline methods such as supervised fine-tuning. We propose a noisy expert model to explain this gap, in which the learner only has access to a noisy version of the expert's policy, but wishes to compete against the reward achieved by a clean expert, motivated by the fact that in many applications, e.g. training language models to perform long chains of thought, the expert is often imperfect. In this setting, we show a sharp separation between offline and online IL. Offline learning from noisy trajectories is fundamentally hard: to compete with the clean expert, the sample complexity must grow exponentially, in contradistinction to the clean expert setting where no explicit horizon dependence exists. In contrast, we prove that online interaction with the noisy expert via a novel variant of OPD enables polynomial dependence on the horizon in general. We further show that, under a natural condition on the expert noise distribution, which we show to be necessary for any horizon-free sample complexity, one can obtain such a guarantee, although our proposed algorithm sacrifices statistical efficiency in its dependence on the size of the policy class. Our analysis leads to an alternative loss function that is commonly considered empirically for LM training. We further provide algorithms and lower bounds, and extend our results to the more realistic setting of unknown corruption when the clean expert is deterministic, thereby providing a theoretical foundation for why OPD can outperform SFT when training language models from imperfect teachers.

cs.LG↗

arXiv2026

Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models

Many modern Language Model (LM) pipelines return an averaged model, such as an exponential moving average of the training iterates, rather than the final iterate itself. This raises a fundamental question: given that we will return an iterate average, how should we change training to improve the performance of this average? We study this question by formulating optimizer design for the iterate-average estimator as an optimal-control problem. In a continuous-time stochastic quadratic model, we solve for the control strategy that minimizes the error of the returned average subject to a penalty on the size of the intervention. A practical approximation to this controller yields PACE, a lightweight wrapper around AdamW that pulls the live weights toward their exponential moving average with a clipped, per-coordinate control strength. We prove that a stylized version of PACE converges at the standard stochastic convex optimization rate, up to a factor depending on the averaging rule, while in the quadratic setting it can strictly improve the limiting squared error of the iterate-average estimator and can do so by an arbitrarily large factor on some instances. Empirically, our results suggest that PACE improves over AdamW and EMA-evaluated AdamW in supervised fine-tuning of 1-2B parameter LMs and in GPT-2 pretraining on FineWeb for a wide range of learning rates, decay schedules, and other hyperparameters.

cs.LG↗

arXiv2026

From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism

Inference-time compute scaling has emerged as a powerful paradigm for improving language model performance on a wide range of tasks, but the question of how best to use the additional compute remains open. A popular approach is BoN sampling, where N candidate responses are generated, scored according to a reward model, and the highest-scoring response is selected. While this approach can improve performance, it is vulnerable to reward hacking, where performance degrades as N increases due to the selection of responses that exploit imperfections in the reward model instead of genuinely improving generation quality. Prior attempts to mitigate reward hacking, via stronger reward models or heavy-handed distributional regularization, either fail to fully address over-optimization or are too conservative to exploit additional compute. In this work, we explore the principle of pessimism in RL, which uses lower confidence bounds on value estimates to avoid OOD actions with uncertain reward estimates. Our approach, termed as caution, can be seen as the reverse of curiosity: where curiosity rewards prediction error as a signal of novelty, caution penalizes prediction error as a signal of distributional uncertainty. Practically, caution trains an error model on typical responses and uses its prediction error to lower reward estimates for atypical ones. Our extensive empirical evaluation demonstrates that caution is a simple, computationally efficient approach that substantially mitigates reward hacking in BoN sampling. We also provide a theoretical analysis in a simplified linear setting, which shows that caution provably improves over the standard BoN approach. Together, our results not only establish caution as a practical solution to reward hacking, but also provide evidence that curiosity-based approaches can be a general OOD detection technique in LLM settings.

cs.LG↗

arXiv2026

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment

Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a reference model and the one with the highest predicted reward according to a learned reward model is selected. Despite its widespread practical use, recent theoretical work has suggested that it is statistically suboptimal and vulnerable to reward hacking, the process by which models exploit weaknesses in the learned reward model to achieve high estimated reward without genuinely improving performance. We revisit this question under assumptions that more closely reflect practice than that of prior work. In particular, in contradistinction to earlier analyses that focused on expected true reward, which may not be meaningful in many practical settings, we investigate how inference-time alignment affects the win-rate, a pairwise comparison-based metric more closely aligned with how reward models are trained and evaluated in practice. We demonstrate that, under minimal conditions on the quality of the reference model and learned reward model, properly tuned BoN is both computationally and statistically optimal in achieving high win-rate, partially explaining its widespread practical success. Because BoN remains susceptible to reward-hacking in this setting, we propose a simple and practical variant that provably eliminates reward-hacking while maintaining optimal statistical performance. Finally, we show that prior approaches are provably suboptimal when considering win-rate, highlighting the importance of choosing appropriate objectives when analyzing inference-time alignment methods.

cs.LG↗

arXiv2026

Partition Function Estimation under Bounded f-Divergence

We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio for a target distribution. While partition function estimation is a classical problem, existing guarantees typically rely on structural assumptions about the domain or model geometry. We instead provide a general, information-theoretic characterization that depends only on the relationship between the proposal and target distributions. Our analysis introduces the integrated coverage profile, a functional that quantifies how much target mass lies in regions where the density ratio is large. We show that integrated coverage tightly characterizes the sample complexity of multiplicative partition function estimation and provide matching lower bounds. We further express these bounds in terms of $f$-divergences, yielding sharp phase transitions depending on the growth rate of f and recovering classical results as a special case while extending to heavy-tailed regimes. Matching lower bounds establish tightness in all regimes. As applications, we derive improved finite-sample guarantees for importance sampling and self-normalized importance sampling, and we show a strict separation between the complexity of approximate sampling and counting under the same divergence constraints. Our results unify and generalize prior analyses of importance sampling, rejection sampling, and heavy-tailed mean estimation, providing a minimal-assumption theory of partition function estimation. Along the way we introduce new technical tools including new connections between coverage and $f$-divergences as well as a generalization of the classical Paley-Zygmund inequality.

stat.ML↗

arXiv2025

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking

Watermarking aims to embed hidden signals in generated text that can be reliably detected when given access to a secret key. Open-weight language models pose acute challenges for such watermarking schemes because the inference-time interventions that dominate contemporary approaches cannot be enforced once model weights are public. Existing watermaking techniques for open-weight models, such as the recently proposed GaussMark, typically rely on small modifications to model weights, which can yield signals detectable to those equipped with a secret key, but achieving detection power comparable to inference-time watermarks generally requires weight perturbations that noticeably reduce generation quality. We introduce MarkTune, a theoretically principled, on-policy fine-tuning framework that treats the GaussMark signal as a reward while simultaneously regularizing against degradation in text quality. We derive MarkTune as an improvement on GaussMark and demonstrate that MarkTune consistently improves the quality-detectability trade-off over GaussMark by steering finer-grained, watermark-aware weight updates within the model's representation space while preserving generation quality. Empirically, we show that MarkTune pushes the quality-detectability frontier of GaussMark close to that of inference-time watermarking, remains robust to paraphrasing and fine-tuning attacks, and exhibits strong generalization: a model fine-tuned on one dataset retains substantial watermark detection power on unseen datasets. Together, these results establish MarkTune as a general strategy for embedding robust, high-quality watermarks into open-weight LMs.

cs.LG↗

arXiv2025

The Coverage Principle: How Pre-Training Enables Post-Training

Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the final model remains poorly understood. Notably, although pre-training success is often quantified by cross-entropy loss, cross-entropy can be a poor predictor of downstream performance. Instead, we provide a theoretical perspective on this relationship through the lens of \emph{coverage}, which quantifies the probability mass the pre-trained model places on high-quality responses and which is necessary and sufficient for post-training and test-time scaling methods such as Best-of-N to succeed. Our main results develop an understanding of \emph{the coverage principle}, a phenomenon whereby next-token prediction (more generally, maximum likelihood) implicitly optimizes toward a model with good coverage. In particular, we uncover a mechanism that explains the power of coverage in predicting downstream performance: \emph{coverage generalizes faster than cross-entropy}, avoiding spurious dependence on problem-dependent parameters such as the sequence length. We also study practical algorithmic interventions with provable benefits for improving coverage, including (i) model/checkpoint selection procedures, (ii) gradient normalization schemes, and (iii) test-time decoding strategies.

stat.ML↗

arXiv2025

EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes

Stochasticity in language model fine-tuning, often caused by the small batch sizes typically used in this regime, can destabilize training by introducing large oscillations in generation quality. A popular approach to mitigating this instability is to take an Exponential moving average (EMA) of weights throughout training. While EMA reduces stochasticity, thereby smoothing training, the introduction of bias from old iterates often creates a lag in optimization relative to vanilla training. In this work, we propose the Bias-Corrected Exponential Moving Average (BEMA), a simple and practical augmentation of EMA that retains variance-reduction benefits while eliminating bias. BEMA is motivated by a simple theoretical model wherein we demonstrate provable acceleration of BEMA over both a standard EMA and vanilla training. Through an extensive suite of experiments on Language Models, we show that BEMA leads to significantly improved convergence rates and final performance over both EMA and vanilla training in a variety of standard LM benchmarks, making BEMA a practical and theoretically motivated intervention for more stable and efficient fine-tuning.

cs.LG↗

arXiv2025

Stellar tidal streams around nearby spiral galaxies with deep imaging from amateur telescopes

Tidal interactions between massive galaxies and their satellites are fundamental processes in a Universe with L-Cold Dark Matter cosmology, redistributing material into faint features that preserve records of past galactic interactions. While stellar streams in the Local Group impressively demonstrate satellite disruption, they do not constitute a statistically significant sample. Constructing a substantial catalog of stellar streams beyond the Local Group remains challenging due to the difficulties in obtaining deep, wide-field images of galaxies. Despite their potential to illuminate dark matter distribution and galaxy formation processes, stellar streams remain underutilized as cosmological probes. The Stellar Tidal Stream Survey (STSS) addresses this observational gap by leveraging amateur telescopes to obtain deep, scientific-grade images of galactic outskirts, capable of building a more statistically meaningful sample of stellar streams. Over the last decade, the STSS has acquired deep (up to surface brightness limit 28.3 mag/arcsec^2 in the r-band), wide-field images of 15 nearby Milky Way analog galaxies using a network of robotic amateur telescopes, avoiding the issues associated with "mosaicing" smaller images taken with a professional telescope. Our survey has revealed a diverse range of previously unreported faint features related to dwarf satellite accretion - including stellar streams, shells, and umbrella-like structures. We discover an ultra-diffuse galaxy (NGC150-UDG1), which shows hints of tidal tails. The STSS demonstrates the suitability of modern amateur telescopes to detect and study faint, diffuse structures in large fields around nearby spiral galaxies. Their economic and accessibility advantages enable larger samples with deep imaging, essential for testing galaxy formation models and constraining the properties of minor merger events in the local Universe.

astro-ph.GA↗

arXiv2025

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment

Inference-time computation offers a powerful axis for scaling the performance of language models. However, naively increasing computation in techniques like Best-of-N sampling can lead to performance degradation due to reward hacking. Toward a theoretical understanding of how to best leverage additional computation, we focus on inference-time alignment, which we formalize as the problem of improving the quality of responses drawn from a pre-trained policy, given a prompt of interest and access to an imperfect reward model. We analyze the performance of inference-time alignment algorithms in terms of (i) response quality, and (ii) compute, and provide new results that highlight the importance of the pre-trained policy's coverage over high-quality responses for performance and compute scaling: 1. We show that Best-of-$N$ alignment with an ideal choice for $N$ can achieve optimal performance under stringent notions of coverage, but provably suffers from reward hacking when $N$ is large, and fails to achieve tight guarantees under more realistic coverage conditions. 2. We introduce $\texttt{InferenceTimePessimism}$, a new algorithm which mitigates reward hacking through deliberate use of inference-time compute, implementing the principle of pessimism in the face of uncertainty via rejection sampling; we prove that its performance is optimal and does not degrade with $N$, meaning it is scaling-monotonic. We complement our theoretical results with an experimental evaluation that demonstrate the benefits of $\texttt{InferenceTimePessimism}$ across a variety of tasks and models.

cs.AI↗

arXiv2025

A Theory of Learning with Autoregressive Chain of Thought

For a given base class of sequence-to-next-token generators, we consider learning prompt-to-answer mappings obtained by iterating a fixed, time-invariant generator for multiple steps, thus generating a chain-of-thought, and then taking the final token as the answer. We formalize the learning problems both when the chain-of-thought is observed and when training only on prompt-answer pairs, with the chain-of-thought latent. We analyze the sample and computational complexity both in terms of general properties of the base class (e.g. its VC dimension) and for specific base classes such as linear thresholds. We present a simple base class that allows for universal representability and computationally tractable chain-of-thought learning. Central to our development is that time invariance allows for sample complexity that is independent of the length of the chain-of-thought. Attention arises naturally in our construction.

stat.ML↗

arXiv2025

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification

Next-token prediction with the logarithmic loss is a cornerstone of autoregressive sequence modeling, but, in practice, suffers from error amplification, where errors in the model compound and generation quality degrades as sequence length $H$ increases. From a theoretical perspective, this phenomenon should not appear in well-specified settings, and, indeed, a growing body of empirical work hypothesizes that misspecification, where the learner is not sufficiently expressive to represent the target distribution, may be the root cause. Under misspecification -- where the goal is to learn as well as the best-in-class model up to a multiplicative approximation factor $C\geq 1$ -- we confirm that $C$ indeed grows with $H$ for next-token prediction, lending theoretical support to this empirical hypothesis. We then ask whether this mode of error amplification is avoidable algorithmically, computationally, or information-theoretically, and uncover inherent computational-statistical tradeoffs. We show: (1) Information-theoretically, one can avoid error amplification and achieve $C=O(1)$. (2) Next-token prediction can be made robust so as to achieve $C=\tilde O(H)$, representing moderate error amplification, but this is an inherent barrier: any next-token prediction-style objective must suffer $C=\Omega(H)$. (3) For the natural testbed of autoregressive linear models, no computationally efficient algorithm can achieve sub-polynomial approximation factor $C=e^{(\log H)^{1-\Omega(1)}}$; however, at least for binary token spaces, one can smoothly trade compute for statistical power and improve on $C=\Omega(H)$ in sub-exponential time. Our results have consequences in the more general setting of imitation learning, where the widely-used behavior cloning algorithm generalizes next-token prediction.

cs.LG↗

arXiv2025

Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective

In order to develop practical and efficient algorithms while circumventing overly pessimistic computational lower bounds, recent work has been interested in developing oracle-efficient algorithms in a variety of learning settings. Two such settings of particular interest are online and differentially private learning. While seemingly different, these two fields are fundamentally connected by the requirement that successful algorithms in each case satisfy stability guarantees; in particular, recent work has demonstrated that algorithms for online learning whose performance adapts to beneficial problem instances, attaining the so-called small-loss bounds, require a form of stability similar to that of differential privacy. In this work, we identify the crucial role that separation plays in allowing oracle-efficient algorithms to achieve this strong stability. Our notion, which we term $\rho$-separation, generalizes and unifies several previous approaches to enforcing this strong stability, including the existence of small-separator sets and the recent notion of $\gamma$-approximability. We present an oracle-efficient algorithm that is capable of achieving small-loss bounds with improved rates in greater generality than previous work, as well as a variant for differentially private learning that attains optimal rates, again under our separation condition. In so doing, we prove a new stability result for minimizers of a Gaussian process that strengthens and generalizes previous work.

cs.LG↗

arXiv2025

GaussMark: A Practical Approach for Structural Watermarking of Language Models

Recent advances in Large Language Models (LLMs) have led to significant improvements in natural language processing tasks, but their ability to generate human-quality text raises significant ethical and operational concerns in settings where it is important to recognize whether or not a given text was generated by a human. Thus, recent work has focused on developing techniques for watermarking LLM-generated text, i.e., introducing an almost imperceptible signal that allows a provider equipped with a secret key to determine if given text was generated by their model. Current watermarking techniques are often not practical due to concerns with generation latency, detection time, degradation in text quality, or robustness. Many of these drawbacks come from the focus on token-level watermarking, which ignores the inherent structure of text. In this work, we introduce a new scheme, GaussMark, that is simple and efficient to implement, has formal statistical guarantees on its efficacy, comes at no cost in generation latency, and embeds the watermark into the weights of the model itself, providing a structural watermark. Our approach is based on Gaussian independence testing and is motivated by recent empirical observations that minor additive corruptions to LLM weights can result in models of identical (or even improved) quality. We show that by adding a small amount of Gaussian noise to the weights of a given LLM, we can watermark the model in a way that is statistically detectable by a provider who retains the secret key. We provide formal statistical bounds on the validity and power of our procedure. Through an extensive suite of experiments, we demonstrate that GaussMark is reliable, efficient, and relatively robust to corruptions such as insertions, deletions, substitutions, and roundtrip translations and can be instantiated with essentially no loss in model quality.

cs.CR↗

arXiv2024

Self-Improvement in Language Models: The Sharpening Mechanism

Recent work in language modeling has raised the possibility of self-improvement, where a language models evaluates and refines its own generations to achieve higher performance without external feedback. It is impossible for this self-improvement to create information that is not already in the model, so why should we expect that this will lead to improved capabilities? We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening. Motivated by the observation that language models are often better at verifying response quality than they are at generating correct responses, we formalize self-improvement as using the model itself as a verifier during post-training in order to ``sharpen'' the model to one placing large mass on high-quality sequences, thereby amortizing the expensive inference-time computation of generating good sequences. We begin by introducing a new statistical framework for sharpening in which the learner aims to sharpen a pre-trained base policy via sample access, and establish fundamental limits. Then we analyze two natural families of self-improvement algorithms based on SFT and RLHF. We find that (i) the SFT-based approach is minimax optimal whenever the initial model has sufficient coverage, but (ii) the RLHF-based approach can improve over SFT-based self-improvement by leveraging online exploration, bypassing the need for coverage. Finally, we empirically validate the sharpening mechanism via inference-time and amortization experiments. We view these findings as a starting point toward a foundational understanding that can guide the design and evaluation of self-improvement algorithms.

cs.AI↗

arXiv2024

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approach to IL, behavior cloning (BC), is thought to incur sample complexity with unfavorable quadratic dependence on the problem horizon, motivating a variety of different online algorithms that attain improved linear horizon dependence under stronger assumptions on the data and the learner's access to the expert. We revisit the apparent gap between offline and online IL from a learning-theoretic perspective, with a focus on the realizable/well-specified setting with general policy classes up to and including deep neural networks. Through a new analysis of behavior cloning with the logarithmic loss, we show that it is possible to achieve horizon-independent sample complexity in offline IL whenever (i) the range of the cumulative payoffs is controlled, and (ii) an appropriate notion of supervised learning complexity for the policy class is controlled. Specializing our results to deterministic, stationary policies, we show that the gap between offline and online IL is smaller than previously thought: (i) it is possible to achieve linear dependence on horizon in offline IL under dense rewards (matching what was previously only known to be achievable in online IL); and (ii) without further assumptions on the policy class, online IL cannot improve over offline IL with the logarithmic loss, even in benign MDPs. We complement our theoretical results with experiments on standard RL tasks and autoregressive language generation to validate the practical relevance of our findings.

cs.LG↗

arXiv2024

On the Performance of Empirical Risk Minimization with Smoothed Data

In order to circumvent statistical and computational hardness results in sequential decision-making, recent work has considered smoothed online learning, where the distribution of data at each time is assumed to have bounded likeliehood ratio with respect to a base measure when conditioned on the history. While previous works have demonstrated the benefits of smoothness, they have either assumed that the base measure is known to the learner or have presented computationally inefficient algorithms applying only in special cases. This work investigates the more general setting where the base measure is \emph{unknown} to the learner, focusing in particular on the performance of Empirical Risk Minimization (ERM) with square loss when the data are well-specified and smooth. We show that in this setting, ERM is able to achieve sublinear error whenever a class is learnable with iid data; in particular, ERM achieves error scaling as $\tilde O( \sqrt{\mathrm{comp}(\mathcal F)\cdot T} )$, where $\mathrm{comp}(\mathcal F)$ is the statistical complexity of learning $\mathcal F$ with iid data. In so doing, we prove a novel norm comparison bound for smoothed data that comprises the first sharp norm comparison for dependent data applying to arbitrary, nonlinear function classes. We complement these results with a lower bound indicating that our analysis of ERM is essentially tight, establishing a separation in the performance of ERM between smoothed and iid data.

stat.ML↗

arXiv2024

Oracle-Efficient Differentially Private Learning with Public Data

Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the performance of private learning algorithms. In this model, algorithms must always guarantee differential privacy with respect to the private samples while also ensuring learning guarantees when the private data distribution is sufficiently close to that of the public data. Previous work has demonstrated that when sufficient public, unlabelled data is available, private learning can be made statistically tractable, but the resulting algorithms have all been computationally inefficient. In this work, we present the first computationally efficient, algorithms to provably leverage public data to learn privately whenever a function class is learnable non-privately, where our notion of computational efficiency is with respect to the number of calls to an optimization oracle for the function class. In addition to this general result, we provide specialized algorithms with improved sample complexities in the special cases when the function class is convex or when the task is binary classification.

stat.ML↗