arXiv subjects

Peng Zhao

Publications and source records attributed to Peng Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2026

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs

Non-stationary parametric bandits have attracted much attention recently. There are three principled ways to deal with non-stationarity, including sliding-window, weighted, and restart strategies. As many non-stationary environments exhibit gradual drifting patterns, the weighted strategy is commonly adopted in real-world applications. However, previous theoretical studies show that its analysis is more involved and the algorithms are either computationally less efficient or statistically suboptimal. This paper revisits the weighted strategy for non-stationary parametric bandits. In linear bandits (LB), we discover that this undesirable feature is due to an inadequate regret analysis, which results in an overly complex algorithm design. We propose a \emph{refined analysis framework}, which simplifies the derivation and, importantly, produces a simpler weight-based algorithm that is as efficient as window/restart-based algorithms while retaining the same regret as previous studies. Furthermore, our new framework can be used to improve regret bounds of other parametric bandits, including Generalized Linear Bandits (GLB) and Self-Concordant Bandits (SCB). For example, we develop a simple weighted GLB algorithm with an $\tilde{O}(k_μ^{5/4} c_μ^{-3/4} d^{3/4} P_T^{1/4}T^{3/4})$ regret, improving the $\tilde{O}(k_μ^{2} c_μ^{-1}d^{9/10} P_T^{1/5}T^{4/5})$ bound in prior work, where $k_μ$ and $c_μ$ characterize the reward model's nonlinearity, $P_T$ measures the non-stationarity, $d$ and $T$ denote the dimension and time horizon. Moreover, we extend our framework to non-stationary Markov Decision Processes (MDPs) with function approximation, focusing on Linear Mixture MDP and Multinomial Logit (MNL) Mixture MDP. For both classes, we propose algorithms based on the weighted strategy and establish dynamic regret guarantees using our analysis framework.

cs.LG↗

arXiv2025

Optimal Model Selection for Conformalized Robust Optimization

In decision-making under uncertainty, Contextual Robust Optimization (CRO) provides reliability by minimizing the worst-case decision loss over a prediction set. While recent advances use conformal prediction to construct prediction sets for machine learning models, the downstream decisions critically depend on model selection. This paper introduces novel model selection frameworks for CRO that unify robustness control with decision risk minimization. We first propose Conformalized Robust Optimization with Model Selection (CROMS), a framework that selects the model to approximately minimize the averaged decision risk in CRO solutions. Given the target robustness level 1-α, we present a computationally efficient algorithm called E-CROMS, which achieves asymptotic robustness control and decision optimality. To correct the control bias in finite samples, we further develop two algorithms: F-CROMS, which ensures a 1-αrobustness but requires searching the label space; and J-CROMS, which offers lower computational cost while achieving a 1-2αrobustness. Furthermore, we extend the CROMS framework to the individualized setting, where model selection is performed by minimizing the conditional decision risk given the covariates of the test data. This framework advances conformal prediction methodology by enabling covariate-aware model selection. Numerical results demonstrate significant improvements in decision efficiency across diverse synthetic and real-world applications, outperforming baseline approaches.

stat.ML↗

arXiv2025

U(1) Gauge Potentials on de Sitter Spacetime

The smooth 1-form Verma module of $\mathfrak{so}(1,4)$ is acquired, which can be regarded as the U(1) gauge potential on de Sitter spacetime. It is shown that electromagnetic fields could not be source free on de Sitter background.

hep-th↗

arXiv2025

A Difference Formula for Tensor-power Multiplicities

A novel combinatorial formula is developed for for tensor product multiplicities in representation theory. We introduce a difference formula linking these multiplicities to restricted occupancy coefficients via a shifted operator. This method is extended to derive branching rules for subalgebras and is conjecturally applied to A-type Lie superalgebras.

math.RT↗

arXiv2025

Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization

Universal online learning aims to achieve optimal regret guarantees without requiring prior knowledge of the curvature of online functions. Existing methods have established minimax-optimal regret bounds for universal online learning, where a single algorithm can simultaneously attain $\mathcal{O}(\sqrt{T})$ regret for convex functions, $\mathcal{O}(d \log T)$ for exp-concave functions, and $\mathcal{O}(\log T)$ for strongly convex functions, where $T$ is the number of rounds and $d$ is the dimension of the feasible domain. However, these methods still lack problem-dependent adaptivity. In particular, no universal method provides regret bounds that scale with the gradient variation $V_T$, a key quantity that plays a crucial role in applications such as stochastic optimization and fast-rate convergence in games. In this work, we introduce UniGrad, a novel approach that achieves both universality and adaptivity, with two distinct realizations: UniGrad.Correct and UniGrad.Bregman. Both methods achieve universal regret guarantees that adapt to gradient variation, simultaneously attaining $\mathcal{O}(\log V_T)$ regret for strongly convex functions and $\mathcal{O}(d \log V_T)$ regret for exp-concave functions. For convex functions, the regret bounds differ: UniGrad.Correct achieves an $\mathcal{O}(\sqrt{V_T \log V_T})$ bound while preserving the RVU property that is crucial for fast convergence in online games, whereas UniGrad.Bregman achieves the optimal $\mathcal{O}(\sqrt{V_T})$ regret bound through a novel design. Both methods employ a meta algorithm with $\mathcal{O}(\log T)$ base learners, which naturally requires $\mathcal{O}(\log T)$ gradient queries per round. To enhance computational efficiency, we introduce UniGrad++, which retains the regret while reducing the gradient query to just $1$ per round via surrogate optimization. We further provide various implications.

cs.LG↗

arXiv2025

Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality

In this work, we study offline convex optimization with smooth objectives, where the classical Nesterov's Accelerated Gradient (NAG) method achieves the optimal accelerated convergence. Extensive research has aimed to understand NAG from various perspectives, and a recent line of work approaches this from the viewpoint of online learning and online-to-batch conversion, emphasizing the role of optimistic online algorithms for acceleration. In this work, we contribute to this perspective by proposing novel optimistic online-to-batch conversions that incorporate optimism theoretically into the analysis, thereby significantly simplifying the online algorithm design while preserving the optimal convergence rates. Specifically, we demonstrate the effectiveness of our conversions through the following results: (i) when combined with simple online gradient descent, our optimistic conversion achieves the optimal accelerated convergence; (ii) our conversion also applies to strongly convex objectives, and by leveraging both optimistic online-to-batch conversion and optimistic online algorithms, we achieve the optimal accelerated convergence rate for strongly convex and smooth objectives, for the first time through the lens of online-to-batch conversion; (iii) our optimistic conversion can achieve universality to smoothness -- applicable to both smooth and non-smooth objectives without requiring knowledge of the smoothness coefficient -- and remains efficient as non-universal methods by using only one gradient query in each iteration. Finally, we highlight the effectiveness of our optimistic online-to-batch conversions by a precise correspondence with NAG.

cs.LG↗

arXiv2025

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness

Smoothness is known to be crucial for acceleration in offline optimization, and for gradient-variation regret minimization in online learning. Interestingly, these two problems are actually closely connected -- accelerated optimization can be understood through the lens of gradient-variation online learning. In this paper, we investigate online learning with Hölder smooth functions, a general class encompassing both smooth and non-smooth (Lipschitz) functions, and explore its implications for offline optimization. For (strongly) convex online functions, we design the corresponding gradient-variation online learning algorithm whose regret smoothly interpolates between the optimal guarantees in smooth and non-smooth regimes. Notably, our algorithms do not require prior knowledge of the Hölder smoothness parameter, exhibiting strong adaptivity over existing methods. Through online-to-batch conversion, this gradient-variation online adaptivity yields an optimal universal method for stochastic convex optimization under Hölder smoothness. However, achieving universality in offline strongly convex optimization is more challenging. We address this by integrating online adaptivity with a detection-based guess-and-check procedure, which, for the first time, yields a universal offline method that achieves accelerated convergence in the smooth regime while maintaining near-optimal convergence in the non-smooth one.

cs.LG↗

arXiv2025

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update

We study the generalized linear bandit (GLB) problem, a contextual multi-armed bandit framework that extends the classical linear model by incorporating a non-linear link function, thereby modeling a broad class of reward distributions such as Bernoulli and Poisson. While GLBs are widely applicable to real-world scenarios, their non-linear nature introduces significant challenges in achieving both computational and statistical efficiency. Existing methods typically trade off between two objectives, either incurring high per-round costs for optimal regret guarantees or compromising statistical efficiency to enable constant-time updates. In this paper, we propose a jointly efficient algorithm that attains a nearly optimal regret bound with $\mathcal{O}(1)$ time and space complexities per round. The core of our method is a tight confidence set for the online mirror descent (OMD) estimator, which is derived through a novel analysis that leverages the notion of mix loss from online prediction. The analysis shows that our OMD estimator, even with its one-pass updates, achieves statistical efficiency comparable to maximum likelihood estimation, thereby leading to a jointly efficient optimistic method.

cs.LG↗

arXiv2025

Provably Efficient Online RLHF with One-Pass Reward Modeling

Reinforcement Learning from Human Feedback (RLHF) has shown remarkable success in aligning Large Language Models (LLMs) with human preferences. Traditional RLHF methods rely on a fixed dataset, which often suffers from limited coverage. To this end, online RLHF has emerged as a promising direction, enabling iterative data collection and refinement. Despite its potential, this paradigm faces a key bottleneck: the requirement to continuously integrate new data into the dataset and re-optimize the model from scratch at each iteration, resulting in computational and storage costs that grow linearly with the number of iterations. In this work, we address this challenge by proposing a one-pass reward modeling method that eliminates the need to store historical data and achieves constant-time updates per iteration. Specifically, we first formalize RLHF as a contextual preference bandit and develop a new algorithm based on online mirror descent with a tailored local norm, replacing the standard maximum likelihood estimation for reward modeling. We then apply it to various online RLHF settings, including passive data collection, active data collection, and deployment-time adaptation. We provide theoretical guarantees showing that our method enhances both statistical and computational efficiency. Finally, we design practical algorithms for LLMs and conduct experiments with the Llama-3-8B-Instruct and Qwen2.5-7B-Instruct models on Ultrafeedback and Mixture2 datasets, validating the effectiveness of our approach.

cs.LG↗

arXiv2025

EdgeSync: Accelerating Edge-Model Updates for Data Drift through Adaptive Continuous Learning

Real-time video analytics systems typically deploy lightweight models on edge devices to reduce latency. However, the distribution of data features may change over time due to various factors such as changing lighting and weather conditions, leading to decreased model accuracy. Recent frameworks try to address this issue by leveraging remote servers to continuously train and adapt lightweight edge models using more complex models in the cloud. Despite these advancements, existing methods face two key challenges: first, the retraining process is compute-intensive, causing significant delays in model updates; second, the new model may not align well with the evolving data distribution of the current video stream. To address these challenges, we introduce EdgeSync, an efficient edge-model updating approach that enhances sample filtering by incorporating timeliness and inference results, thus ensuring training samples are more relevant to the current video content while reducing update delays. Additionally, EdgeSync features a dynamic training management module that optimizes the timing and sequencing of model updates to improve their timeliness. Evaluations on diverse and complex real-world datasets demonstrate that EdgeSync improves accuracy by approximately 3.4% compared to existing methods and by about 10% compared to traditional approaches.

cs.CV↗

arXiv2025

Parameter-free Algorithms for the Stochastically Extended Adversarial Model

We develop the first parameter-free algorithms for the Stochastically Extended Adversarial (SEA) model, a framework that bridges adversarial and stochastic online convex optimization. Existing approaches for the SEA model require prior knowledge of problem-specific parameters, such as the diameter of the domain $D$ and the Lipschitz constant of the loss functions $G$, which limits their practical applicability. Addressing this, we develop parameter-free methods by leveraging the Optimistic Online Newton Step (OONS) algorithm to eliminate the need for these parameters. We first establish a comparator-adaptive algorithm for the scenario with unknown domain diameter but known Lipschitz constant, achieving an expected regret bound of $\tilde{O}\big(\|u\|_2^2 + \|u\|_2(\sqrt{σ^2_{1:T}} + \sqrt{Σ^2_{1:T}})\big)$, where $u$ is the comparator vector and $σ^2_{1:T}$ and $Σ^2_{1:T}$ represent the cumulative stochastic variance and cumulative adversarial variation, respectively. We then extend this to the more general setting where both $D$ and $G$ are unknown, attaining the comparator- and Lipschitz-adaptive algorithm. Notably, the regret bound exhibits the same dependence on $σ^2_{1:T}$ and $Σ^2_{1:T}$, demonstrating the efficacy of our proposed methods even when both parameters are unknown in the SEA model.

cs.LG↗

arXiv2025

LongCat-Flash Technical Report

We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming from the need for scalable efficiency, LongCat-Flash adopts two novel designs: (a) Zero-computation Experts, which enables dynamic computational budget allocation and activates 18.6B-31.3B (27B on average) per token depending on contextual demands, optimizing resource usage. (b) Shortcut-connected MoE, which enlarges the computation-communication overlap window, demonstrating notable gains in inference efficiency and throughput compared to models of a comparable scale. We develop a comprehensive scaling framework for large models that combines hyperparameter transfer, model-growth initialization, a multi-pronged stability suite, and deterministic computation to achieve stable and reproducible training. Notably, leveraging the synergy among scalable architectural design and infrastructure efforts, we complete model training on more than 20 trillion tokens within 30 days, while achieving over 100 tokens per second (TPS) for inference at a cost of \$0.70 per million output tokens. To cultivate LongCat-Flash towards agentic intelligence, we conduct a large-scale pre-training on optimized mixtures, followed by targeted mid- and post-training on reasoning, code, and instructions, with further augmentation from synthetic data and tool use tasks. Comprehensive evaluations demonstrate that, as a non-thinking foundation model, LongCat-Flash delivers highly competitive performance among other leading models, with exceptional strengths in agentic tasks. The model checkpoint of LongCat-Flash is open-sourced to foster community research. LongCat Chat: https://longcat.ai Hugging Face: https://huggingface.co/meituan-longcat GitHub: https://github.com/meituan-longcat

cs.CL↗

arXiv2025

Trapped surface formation for the Einstein-Weyl spinor system

We prove trapped-surface formation for the Einstein-Weyl spinor system (gravity coupled to a massless left-handed two-spinor) without any symmetry assumption. To this end we establish a semi-global solution under double null foliation and show that the focusing of the gravitational waves and the Weyl spinor flux leads to the formation of a trapped surface.

gr-qc↗

arXiv2025

Efficient Methods for Non-stationary Online Learning

Non-stationary online learning has drawn much attention in recent years. In particular, dynamic regret and adaptive regret are proposed as two principled performance measures for online convex optimization in non-stationary environments. To optimize them, a two-layer online ensemble is usually deployed due to the inherent uncertainty of non-stationarity, in which multiple base-learners are maintained and a meta-algorithm is employed to track the best one on the fly. However, the two-layer structure raises concerns about computational complexity -- such methods typically maintain $O(\log T)$ base-learners simultaneously for a $T$-round online game and thus perform multiple projections onto the feasible domain per round, which becomes the computational bottleneck when the domain is complicated. In this paper, we present efficient methods for optimizing dynamic regret and adaptive regret that reduce the number of projections per round from $O(\log T)$ to $1$. The proposed algorithms require only one gradient query and one function evaluation at each round. Our technique hinges on the reduction mechanism developed in parameter-free online learning and requires non-trivial modifications for non-stationary online methods. Furthermore, we study an even stronger measure, namely "interval dynamic regret", and reduce the number of projections per round from $O(\log^2 T)$ to $1$ for minimizing it. Our reduction demonstrates broad generality and applies to two important applications: online stochastic control and online principal component analysis, resulting in methods that are both efficient and optimal. Finally, empirical studies verify our theoretical findings.

cs.LG↗

arXiv2025

R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models

Code completion models have made significant progress in recent years. Recently, repository-level code completion has drawn more attention in modern software development, and several baseline methods and benchmarks have been proposed. However, existing repository-level code completion methods often fall short of fully using the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies. Besides, the existing benchmarks usually focus on limited code completion scenarios, which cannot reflect the repository-level code completion abilities well of existing methods. To address these limitations, we propose the R2C2-Coder to enhance and benchmark the real-world repository-level code completion abilities of code Large Language Models, where the R2C2-Coder includes a code prompt construction method R2C2-Enhance and a well-designed benchmark R2C2-Bench. Specifically, first, in R2C2-Enhance, we first construct the candidate retrieval pool and then assemble the completion prompt by retrieving from the retrieval pool for each completion cursor position. Second, based on R2C2 -Enhance, we can construct a more challenging and diverse R2C2-Bench with training, validation and test splits, where a context perturbation strategy is proposed to simulate the real-world repository-level code completion well. Extensive results on multiple benchmarks demonstrate the effectiveness of our R2C2-Coder.

cs.CL↗

arXiv2025

On the local existence for the characteristic initial value problem for the Einstein-Dirac system

In this paper, we investigate the characteristic initial value problem for the Einstein-Dirac system, a model governing the interaction between gravity and spin-$1/2$ fields. We apply Luk's strategy \cite{Luk12} and prove a semi-global existence result for this coupled Einstein-Dirac system without imposing symmetry conditions. More precisely, we construct smooth solutions in a rectangular region to the future of two intersecting null hypersurfaces, on which characteristic initial data are specified. The key novelty is to promote the symmetric spinorial derivatives of the Dirac field to independent variables and to derive a commuted "Weyl-curvature-free" evolution system for them. This eliminates the coupling to the curvature in the energy estimates and closes the bootstrap at the optimal derivative levels. The analysis relies on a double null foliation and incorporates spinor-specific techniques essential to handling the structure of the Dirac field.

math.AP↗

arXiv2025

Demonstration of Maxwell Demon-assistant Einstein-Podolsky-Rosen Steering via Superconducting Quantum Processor

The concept of Maxwell demon plays an essential role in connecting thermodynamics and information theory, while entanglement and non-locality are fundamental features of quantum theory. Given the rapid advancements in the field of quantum information science, there is a growing interest and significance in investigating the connection between Maxwell demon and quantum correlation. The majority of research endeavors thus far have been directed towards the extraction of work from quantum correlation through the utilization of Maxwell demon. Recently, a novel concept called Maxwell demon-assistant Einstein-Podolsky-Rosen (EPR) steering has been proposed, which suggests that it is possible to simulate quantum correlation by doing work. This seemingly counterintuitive conclusion is attributed to the fact that Alice and Bob need classical communication during EPR steering task, a requirement that does not apply in the Bell test. In this study, we demonstrate Maxwell demon-assistant EPR steering with superconducting quantum circuits. By compiling and optimizing a quantum circuit to be implemented on a 2D superconducting chip, we were able to achieve a steering parameter of $S_{2} = 0.770 \pm 0.005$ in the case of two measurement settings, which surpasses the classical bound of $1/\sqrt{2}$ by 12.6 standard deviations. In addition, experimental observations have revealed a linear correlation between the non-locality demonstrated in EPR steering and the work done by the demon. Considering the errors in practical operation, the experimental results are highly consistent with theoretical predictions. Our findings not only suggest the presence of a Maxwell demon loophole in the EPR steering, but also contribute to a deeper comprehension of the interplay between quantum correlation, information theory, and thermodynamics.

quant-ph↗

arXiv2025

Generative Model-Based Feature Attention Module for Video Action Analysis

Video action analysis is a foundational technology within the realm of intelligent video comprehension, particularly concerning its application in Internet of Things(IoT). However, existing methodologies overlook feature semantics in feature extraction and focus on optimizing action proposals, thus these solutions are unsuitable for widespread adoption in high-performance IoT applications due to the limitations in precision, such as autonomous driving, which necessitate robust and scalable intelligent video analytics analysis. To address this issue, we propose a novel generative attention-based model to learn the relation of feature semantics. Specifically, by leveraging the differences of actions' foreground and background, our model simultaneously learns the frame- and segment-dependencies of temporal action feature semantics, which takes advantage of feature semantics in the feature extraction effectively. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark video task, action recognition and action detection. In the context of action detection tasks, we substantiate the superiority of our approach through comprehensive validation on widely recognized datasets. Moreover, we extend the validation of the effectiveness of our proposed method to a broader task, video action recognition. Our code is available at https://github.com/Generative-Feature-Model/GAF.

cs.CV↗