Search arXiv⌕ Search

arXiv subjects

Peter Bartlett

Publications and source records attributed to Peter Bartlett.

At least 19 recordsLinked to original sources

Statistical Geometry of Group Actions: Symmetry, Transport, Estimation

We study variational inference in the presence of distributional symmetry, focusing on the interaction between two distinct group actions on a sample space: a symmetry action that leaves a reference distribution invariant, and a transport action that generates a parametric variational family by pushforward. By analyzing the algebraic structure of the total transformation group generated by both actions and the induced adjoint representation of the symmetry group on the transport Lie algebra, we establish that the Riemannian gradient of the Kullback--Leibler divergence at the true transport parameter is constrained to lie in the trivial representation of the symmetry group. Consequently, symmetry forces the gradient to vanish along all non-trivial representations. Combining this representation-theoretic constraint with parameter identifiability yields an orthogonal decomposition of the transport Lie algebra into three interpretable subspaces: an identifiability kernel (along which the objective is locally constant), a bias subspace (where the gradient may be nonzero due to model misspecification), and a symmetry-breaking subspace (where the gradient is forced to vanish by symmetry alone). Finally, we characterize the residual bias directions in terms of distributional mismatch between the base model and the standardized target, and derive an explicit Stein-type moment-matching condition that eliminates this bias, extending the location-scale results of (Margossian and Saul, 2025) to general Lie group transformation families.

math.ST↗

Internal Guidance as a Sampling Method for Tilted Diffusion Models

Reward guidance methods sample an exponential tilt of a base density using a diffusion model trained with only samples from the base distribution. Existing methods use what we call external guidance: additive terms in the drift or multiplicative terms on the transition probabilities. We propose internal guidance which leaves the output of the base denoiser unmodified and instead changes the point at which it is evaluated. For discrete distributions embedded in the hypercube $\{-1,1\}^{d}$, the denoiser of any linearly tilted density is exactly the base denoiser evaluated at a shifted and rescaled input. In practice the base denoiser is a neural network trained on noised samples of the base distribution. The required evaluation points for sampling the tilted density would be out-of-distribution for basic noising of the base distribution. We modify the training algorithm with random diagonal rescalings of the data, so that the denoiser network learns both in- and out-of-distribution evaluations of the denoiser relative to the base distribution. A single denoiser network samples binary reward tilts, class labels, and infilling with no fine-tuning and no external guidance term.

stat.ML↗

Improving score-based sampling via affine post-processing

Sampling from a probability distribution with access only to its log-density is a foundational problem in statistics, machine learning, and the physical sciences. This problem is studied in the data-free score-based diffusion literature, which samples the target density via estimating scores of densities produced by convolution with Gaussian random variables and implementing a reverse SDE. In this framework, score estimators are constructed via Markov chain Monte Carlo, importance sampling, or rejection sampling. The estimators often operate far beyond the regime where mixing time and error control can be established and have large bias and variance when estimating the underlying score. In our method we propose post-processing: splitting a fixed computation budget across multiple evaluations, querying the estimator at different points, and fitting a single pooled estimate via linear combination to minimize bias and variance at a target location. The final value is an affine map of a vector of multiple score estimates. We show this reduces score estimation error when compared to the computation-matched base estimator queried at a single point. We demonstrate improved sample quality over other score estimation methods matched for computation cost on difficult target densities such as log-concave densities with large condition number, multimodal densities, and high-dimensional densities.

stat.ME↗

Principal Component Regression Dominates all Monotone Spectral Filters for Linear Regression

We compare the instance-wise, finite-sample risks of monotone spectral filters for linear regression, a broad class of estimators including principal component regression (PCR), gradient descent (GD), and ridge regression. We show that PCR dominates all monotone spectral filters: compared to any such filter, the risk of optimally tuned PCR is no bigger by a constant factor for all problems. Furthermore, the dominance is strong if the filter is separated from step functions (e.g., GD and ridge): there exist problem instances for which the risk of PCR is smaller by a polynomial factor in sample size dependence. Our comparison results show that PCR is optimal and thus admissible among monotone filters, significantly extending Wu et al. (2026)'s result that GD strongly dominates ridge. From a technical perspective, we establish new upper and lower bounds for general spectral filters, which are instance-wise sharp when specialized to ridge or GD, recovering or improving the best-known bounds.

stat.ML↗

Learn Your Own Thoughts: Abstract Token Curriculum

Large Language Models (LLMs) have achieved remarkable reasoning capabilities by utilizing chain-of-thought (CoT) as a scratchpad for intermediate stages of thinking. However, CoT techniques require explicit supervision on thinking tokens, which requires rich, task-specific data. In this work, we propose Abstract Token Curriculum (ATC), a novel curriculum learning framework that elicits effective continuous intermediate representations without direct supervision or manual scratchpad design. ATC gradually increases problem complexity through a sequence of distributions, training the model to develop internal abstract ``thoughts'' in the continuous representation space. This paper provides both theoretical and experimental evidence for the benefits of ATC and its advantages over previous methods for training continuous thoughts. Theoretically, we show that for learning parity functions with single-layer softmax attention using ATC, attention naturally focuses on the CoT tokens in the context that provide the ``easiest path'' to predicting the next token. Experimentally, we show ATC's effectiveness on graph reachability and arithmetic learning tasks.

cs.LG↗

Hard labels sampled from sparse targets mislead rotation invariant algorithms

One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic regression, the feedback can be either soft labels, corresponding to the true conditional probability of the data (as in distillation), or sampled hard labels (taking values $\pm 1$). We point out a fundamental problem that arises even in a particularly favorable setting, where the goal is to learn a noise-free soft target of the form $σ(\mathbf{x}^{\top}\mathbf{w}^{\star})$. In the over-constrained case (i.e. the number of samples $n$ exceeds the input dimension $d$) with examples $(\mathbf{x}_i,σ(\mathbf{x}_i^{\top}\mathbf{w}^{\star}))$, it is sufficient to recover $\mathbf{w}^{\star}$ and hence achieve the Bayes risk. However, we prove that when the examples are labeled by hard labels $y_i$ sampled from the same conditional distribution $σ(\mathbf{x}_i^{\top}\mathbf{w}^{\star})$ and $\mathbf{w}^{\star}$ is $s$-sparse, then rotation-invariant algorithms are provably suboptimal: they incur an excess risk $Ω\!\left(\frac{d-1}{n}\right)$, while there are simple non-rotation invariant algorithms with excess risk $O(\frac{s\log d}{n})$. The simplest rotation invariant algorithm is gradient descent on the logistic loss (with early stopping). A simple non-rotation-invariant algorithm for sparse targets that achieves the above upper bounds uses gradient descent on the weights $u_i,v_i$, where now the linear weight $w_i$ is reparameterized as $u_iv_i$.

stat.ML↗

RubiConv -- Efficient Boundary-Respecting Convolutions

Convolutional architectures have emerged as powerful alternatives to Transformers for sequence modeling. The primary advantage is that they offer improved theoretical sequence length complexity by leveraging the Fast Fourier Transform (FFT). However, this theoretical improvement does not always meaningfully land in practice. One critical obstacle is that applying standard FFTs is not amenable to the large-scale training pipeline wherein data is packed from different sources into a single sequence for hardware efficiency. Indeed, standard FFT algorithms are not easily amenable to document packing. Existing workarounds suffer from severe inefficiencies, crippling the practical performance of convolutional architectures. We close this gap with RubiConv, a novel algorithm for performing hardware-efficient, boundary-respecting convolutions on packed sequences. Extensive experiments show that RubiConv achieves significant speedups over both attention and standard FFT-based baselines. This work makes the theoretical efficiency of long convolutional models a practical reality for large-scale, real-world data packing.

cs.LG↗

Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention parameters at a geometric rate. Our analysis proceeds in two steps. First, we show that in the infinite-data limit the regression problem solved by the self-attention layer is equivalent to a nonconvex matrix factorization problem. Second, we exploit this connection to design a novel "structure-aware" variant of gradient descent which efficiently optimizes the original finite-data regression objective. Our optimization algorithm features several innovations over standard gradient descent, including a preconditioner and regularizer which help avoid spurious stationary points, and a data-dependent spectral initialization of parameters which lie near the manifold of global minima with high probability.

cs.LG↗

A result relating convex n-widths to covering numbers with some applications to neural networks

In general, approximating classes of functions defined over high-dimensional input spaces by linear combinations of a fixed set of basis functions or ``features'' is known to be hard. Typically, the worst-case error of the best basis set decays only as fast as $Θ\(n^{-1/d}\)$, where $n$ is the number of basis functions and $d$ is the input dimension. However, there are many examples of high-dimensional pattern recognition problems (such as face recognition) where linear combinations of small sets of features do solve the problem well. Hence these function classes do not suffer from the ``curse of dimensionality'' associated with more general classes. It is natural then, to look for characterizations of high-dimensional function classes that nevertheless are approximated well by linear combinations of small sets of features. In this paper we give a general result relating the error of approximation of a function class to the covering number of its ``convex core''. For one-hidden-layer neural networks, covering numbers of the class of functions computed by a single hidden node upper bound the covering numbers of the convex core. Hence, using standard results we obtain upper bounds on the approximation rate of neural network classes.

cs.LG↗

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression

We study gradient descent (GD) with a constant stepsize for $\ell_2$-regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensure monotonic reduction of the optimization objective, achieving exponential convergence in $\widetilde{\mathcal{O}}(κ)$ steps with $κ$ being the condition number. Surprisingly, we show that this can be accelerated to $\widetilde{\mathcal{O}}(\sqrtκ)$ by simply using a large stepsize -- for which the objective evolves nonmonotonically. The acceleration brought by large stepsizes extends to minimizing the population risk for separable distributions, improving on the best-known upper bounds on the number of steps to reach a near-optimum. Finally, we characterize the largest stepsize for the local convergence of GD, which also determines the global convergence in special scenarios. Our results extend the analysis of Wu et al. (2024) from convex settings with minimizers at infinity to strongly convex cases with finite minimizers.

stat.ML↗

Contextual Bandits with Stage-wise Constraints

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise constraint (cost function) are linear. In each of the high probability and in expectation settings, we propose an upper-confidence bound algorithm for the problem and prove a $T$-round regret bound for it. We also prove a lower-bound for this constrained problem, show how our algorithms and analyses can be extended to multiple constraints, and provide simulations to validate our theoretical results. In the high probability setting, we describe the minimum requirements for the action set for our algorithm to be tractable. In the setting that the constraint is in expectation, we specialize our results to multi-armed bandits and propose a computationally efficient algorithm for this setting with regret analysis. Finally, we extend our results to the case where the reward and cost functions are both non-linear. We propose an algorithm for this case and prove a regret bound for it that characterize the function class complexity by the eluder dimension.

cs.LG↗

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work investigates additional regularization effects induced by early stopping in well-specified high-dimensional logistic regression. We first demonstrate that the excess logistic risk vanishes for early-stopped GD but diverges to infinity for GD iterates at convergence. This suggests that early-stopped GD is well-calibrated, whereas asymptotic GD is statistically inconsistent. Second, we show that to attain a small excess zero-one risk, polynomially many samples are sufficient for early-stopped GD, while exponentially many samples are necessary for any interpolating estimator, including asymptotic GD. This separation underscores the statistical benefits of early stopping in the overparameterized regime. Finally, we establish nonasymptotic bounds on the norm and angular differences between early-stopped GD and $\ell_2$-regularized empirical risk minimizer, thereby connecting the implicit regularization of GD with explicit $\ell_2$-regularization.

cs.LG↗

FutureFill: Fast Generation from Convolutional Sequence Models

We address the challenge of efficient auto-regressive generation in sequence prediction models by introducing FutureFill, a general-purpose fast generation method for any sequence prediction algorithm based on convolutional operators. FutureFill reduces generation time from quadratic to quasilinear in the context length. Moreover, when generating from a prompt, it requires a prefill cache whose size grows only with the number of tokens to be generated, often much smaller than the caches required by standard convolutional or attention based models. We validate our theoretical claims with experiments on synthetic tasks and demonstrate substantial efficiency gains when generating from a deep convolutional sequence prediction model.

cs.LG↗

Implicit Diffusion: Efficient Optimization through Stochastic Sampling

We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provide theoretical guarantees on the performance of our method, as well as experimental results demonstrating its effectiveness. We apply it to training energy-based models and finetuning denoising diffusions.

cs.LG↗

Fast Best-of-N Decoding via Speculative Rejection

The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human preferences. Prevalent alignment techniques, such as DPO, PPO and their variants, align LLMs by changing the pre-trained model weights during a phase called post-training. While predominant, these post-training methods add substantial complexity before LLMs can be deployed. Inference-time alignment methods avoid the complex post-training step and instead bias the generation towards responses that are aligned with human preferences. The best-known inference-time alignment method, called Best-of-N, is as effective as the state-of-the-art post-training procedures. Unfortunately, Best-of-N requires vastly more resources at inference time than standard decoding strategies, which makes it computationally not viable. In this work, we introduce Speculative Rejection, a computationally-viable inference-time alignment algorithm. It generates high-scoring responses according to a given reward model, like Best-of-N does, while being between 16 to 32 times more computationally efficient.

cs.CL↗

Can a Transformer Represent a Kalman Filter?

Transformers are a class of autoregressive deep learning architectures which have recently achieved state-of-the-art performance in various vision, language, and robotics tasks. We revisit the problem of Kalman Filtering in linear dynamical systems and show that Transformers can approximate the Kalman Filter in a strong sense. Specifically, for any observable LTI system we construct an explicit causally-masked Transformer which implements the Kalman Filter, up to a small additive error which is bounded uniformly in time; we call our construction the Transformer Filter. Our construction is based on a two-step reduction. We first show that a softmax self-attention block can exactly represent a Nadaraya-Watson kernel smoothing estimator with a Gaussian kernel. We then show that this estimator closely approximates the Kalman Filter. We also investigate how the Transformer Filter can be used for measurement-feedback control and prove that the resulting nonlinear controllers closely approximate the performance of standard optimal control policies such as the LQG controller.

cs.LG↗

Parallelizing Contextual Bandits

Standard approaches to decision-making under uncertainty focus on sequential exploration of the space of decisions. However, \textit{simultaneously} proposing a batch of decisions, which leverages available resources for parallel experimentation, has the potential to rapidly accelerate exploration. We present a family of (parallel) contextual bandit algorithms applicable to problems with bounded eluder dimension whose regret is nearly identical to their perfectly sequential counterparts -- given access to the same total number of oracle queries -- up to a lower-order ``burn-in" term. We further show these algorithms can be specialized to the class of linear reward functions where we introduce and analyze several new linear bandit algorithms which explicitly introduce diversity into their action selection. Finally, we also present an empirical evaluation of these parallel algorithms in several domains, including materials discovery and biological sequence design problems, to demonstrate the utility of parallelized bandits in practical settings.

stat.ML↗

A Complete Characterization of Linear Estimators for Offline Policy Evaluation

Offline policy evaluation is a fundamental statistical problem in reinforcement learning that involves estimating the value function of some decision-making policy given data collected by a potentially different policy. In order to tackle problems with complex, high-dimensional observations, there has been significant interest from theoreticians and practitioners alike in understanding the possibility of function approximation in reinforcement learning. Despite significant study, a sharp characterization of when we might expect offline policy evaluation to be tractable, even in the simplest setting of linear function approximation, has so far remained elusive, with a surprising number of strong negative results recently appearing in the literature. In this work, we identify simple control-theoretic and linear-algebraic conditions that are necessary and sufficient for classical methods, in particular Fitted Q-iteration (FQI) and least squares temporal difference learning (LSTD), to succeed at offline policy evaluation. Using this characterization, we establish a precise hierarchy of regimes under which these estimators succeed. We prove that LSTD works under strictly weaker conditions than FQI. Furthermore, we establish that if a problem is not solvable via LSTD, then it cannot be solved by a broad class of linear estimators, even in the limit of infinite data. Taken together, our results provide a complete picture of the behavior of linear estimators for offline policy evaluation, unify previously disparate analyses of canonical algorithms, and provide significantly sharper notions of the underlying statistical complexity of offline policy evaluation.

cs.LG↗