arXiv subjects

Zhi-Hua Zhou

Publications and source records attributed to Zhi-Hua Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs

With the rapid advancement of human science and technology, problems in industrial scenarios are becoming increasingly challenging, bringing significant challenges to traditional algorithm design. Automated algorithm design with LLMs emerges as a promising solution, but the currently adopted black-box modeling deprives LLMs of any awareness of the intrinsic mechanism of the target problem, leading to hallucinated designs. In this paper, we introduce Evolutionary Stagewise Algorithm Design (EvoStage), a novel evolutionary paradigm that bridges the gap between the rigorous demands of industrial-scale algorithm design and the LLM-based algorithm design methods. Drawing inspiration from CoT, EvoStage decomposes the algorithm design process into sequential, manageable stages and integrates real-time intermediate feedback to iteratively refine algorithm design directions. To further reduce the algorithm design space and avoid falling into local optima, we introduce a multi-agent system and a "global-local perspective" mechanism. We apply EvoStage to the design of two types of common optimizers: designing parameter configuration schedules of the Adam optimizer for chip placement, and designing acquisition functions of Bayesian optimization for black-box optimization. Experimental results across open-source benchmarks demonstrate that EvoStage outperforms human-expert designs and existing LLM-based methods within only a couple of evolution steps, even achieving the historically state-of-the-art half-perimeter wire-length results on every tested chip case. Furthermore, when deployed on a commercial-grade 3D chip placement tool, EvoStage significantly surpasses the original performance metrics, achieving record-breaking efficiency. We hope EvoStage can significantly advance automated algorithm design in the real world, helping elevate human productivity.

cs.AI↗

arXiv2026

Theoretical Investigation on Inductive Bias of Isolation Forest

Isolation Forest (iForest) stands out as a widely-used unsupervised anomaly detector, primarily owing to its remarkable runtime efficiency and superior performance in large-scale tasks. Despite its widespread adoption, a theoretical foundation explaining iForest's success remains unclear. This paper focuses on the inductive bias of iForest, which theoretically elucidates under what circumstances and to what extent iForest works well. The key is to formulate the growth process of iForest, where the split dimensions and split values are randomly selected. We model the growth process of iForest as a random walk, enabling us to derive the expected depth function, which is the outcome of iForest, using transition probabilities. The case studies reveal key inductive biases: iForest exhibits lower sensitivity to central anomalies while demonstrating greater parameter adaptability compared to $k$-Nearest Neighbor. Our study provides a theoretical understanding of the effectiveness of iForest and establishes a foundation for further theoretical exploration.

cs.LG↗

arXiv2026

AeroSketch: Near-Optimal Time Matrix Sketch Framework for Persistent, Sliding Window, and Distributed Streams

Many real-world matrix datasets arrive as high-throughput vector streams, making it impractical to store or process them in their entirety. To enable real-time analytics under limited computational, memory, and communication resources, matrix sketching techniques have been developed over recent decades to provide compact approximations of such streaming data. Some algorithms have achieved optimal space and communication complexity. However, these approaches often require frequent time-consuming matrix factorization operations. In particular, under tight approximation error bounds, each matrix factorization computation incurs cubic time complexity, thereby limiting their update efficiency. In this paper, we introduce AeroSketch, a novel matrix sketching framework that leverages recent advances in randomized numerical linear algebra (RandNLA). AeroSketch achieves optimal communication and space costs while delivering near-optimal update time complexity (within logarithmic factors) across persistent, sliding window, and distributed streaming scenarios. Extensive experiments on both synthetic and real-world datasets demonstrate that AeroSketch consistently outperforms state-of-the-art methods in update throughput. In particular, under tight approximation error constraints, AeroSketch reduces the cubic time complexity to the quadratic level. Meanwhile, it maintains comparable approximation quality while retaining optimal communication and space costs.

cs.DB↗

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

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

Re$^{\text{2}}$MaP: Macro Placement by Recursively Prototyping and Packing Tree-based Relocating

This work introduces the Re$^{\text{2}}$MaP method, which generates expert-quality macro placements through recursively prototyping and packing tree-based relocating. We first perform multi-level macro grouping and PPA-aware cell clustering to produce a unified connection matrix that captures both wirelength and dataflow among macros and clusters. Next, we use DREAMPlace to build a mixed-size placement prototype and obtain reference positions for each macro and cluster. Based on this prototype, we introduce ABPlace, an angle-based analytical method that optimizes macro positions on an ellipse to distribute macros uniformly near chip periphery, while optimizing wirelength and dataflow. A packing tree-based relocating procedure is then designed to jointly adjust the locations of macro groups and the macros within each group, by optimizing an expertise-inspired cost function that captures various design constraints through evolutionary search. Re$^{\text{2}}$MaP repeats the above process: Only a subset of macro groups are positioned in each iteration, and the remaining macros are deferred to the next iteration to improve the prototype's accuracy. Using a well-established backend flow with sufficient timing optimizations, Re$^{\text{2}}$MaP achieves up to 22.22% (average 10.26%) improvement in worst negative slack (WNS) and up to 97.91% (average 33.97%) improvement in total negative slack (TNS) compared to the state-of-the-art academic placer Hier-RTLMP. It also ranks higher on WNS, TNS, power, design rule check (DRC) violations, and runtime than the conference version ReMaP, across seven tested cases. Our code is available at https://github.com/lamda-bbo/Re2MaP.

cs.AR↗

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

Curriculum Abductive Learning

Abductive Learning (ABL) integrates machine learning with logical reasoning in a loop: a learning model predicts symbolic concept labels from raw inputs, which are revised through abduction using domain knowledge and then fed back for retraining. However, due to the nondeterminism of abduction, the training process often suffers from instability, especially when the knowledge base is large and complex, resulting in a prohibitively large abduction space. While prior works focus on improving candidate selection within this space, they typically treat the knowledge base as a static black box. In this work, we propose Curriculum Abductive Learning (C-ABL), a method that explicitly leverages the internal structure of the knowledge base to address the ABL training challenges. C-ABL partitions the knowledge base into a sequence of sub-bases, progressively introduced during training. This reduces the abduction space throughout training and enables the model to incorporate logic in a stepwise, smooth way. Experiments across multiple tasks show that C-ABL outperforms previous ABL implementations, significantly improves training stability, convergence speed, and final accuracy, especially under complex knowledge setting.

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

Extended UCB Policies for Multi-armed Bandit Problems

The multi-armed bandit (MAB) problems are widely studied in fields of operations research, stochastic optimization, and reinforcement learning. In this paper, we consider the classical MAB model with heavy-tailed reward distributions and introduce the extended robust UCB policy, which is an extension of the results of Bubeck et al. [5] and Lattimore [22] that are further based on the pioneering idea of UCB policies [e.g. Auer et al. 3]. The previous UCB policies require some strict conditions on reward distributions, which can be difficult to guarantee in practical scenarios. Our extended robust UCB generalizes Lattimore's seminary work (for moments of orders $p=4$ and $q=2$) to arbitrarily chosen $p>q>1$ as long as the two moments have a known controlled relationship, while still achieving the optimal regret growth order $O(log T)$, thus providing a broadened application area of UCB policies for heavy-tailed reward distributions. Furthermore, we achieve a near-optimal regret order without any knowledge of the reward distributions as long as their $p$-th moments exist for some $p>1$. Finally, we briefly present our earlier work on light-tailed reward distributions for a complete illustration of the amazing simplicity and power of UCB policies.

cs.LG↗

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

Dual Adaptivity: Universal Algorithms for Minimizing the Adaptive Regret of Convex Functions

To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existing algorithms lack universality in the sense that they can only handle one type of convex functions and need apriori knowledge of parameters, which hinders their application in real-world scenarios. To address this limitation, this paper investigates universal algorithms with dual adaptivity, which automatically adapt to the property of functions (convex, exponentially concave, or strongly convex), as well as the nature of environments (stationary or changing). Specifically, we propose a meta-expert framework for dual adaptive algorithms, where multiple experts are created dynamically and aggregated by a meta-algorithm. The meta-algorithm is required to yield a second-order bound, which can accommodate unknown function types. We further incorporate the technique of sleeping experts to capture the changing environments. For the construction of experts, we introduce two strategies (increasing the number of experts or enhancing the capabilities of experts) to achieve universality. Theoretical analysis shows that our algorithms are able to minimize the adaptive regret for multiple types of convex functions simultaneously, and also allow the type of functions to switch between rounds. Moreover, we extend our meta-expert framework to online composite optimization, and develop a universal algorithm for minimizing the adaptive regret of composite functions.

cs.LG↗

arXiv2025

Generalist Reward Models: Found Inside Large Language Models

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical foundation. In this paper, we discover that a powerful generalist reward model is already latently present within any LLM trained via standard next-token prediction. We prove that this endogenous reward is not a heuristic, but is theoretically equivalent to a reward function learned through offline inverse reinforcement learning. This connection allows us to directly elicit a high-quality reward signal from a base (pre-trained or supervised fine-tuned) model without any further training. Critically, we also prove that subsequent reinforcement learning using this endogenous reward leads to a policy with a provably superior error bound compared to the base model. To our best knowledge, this is the first theoretical proof of the effectiveness of reinforcement learning for LLMs. Our experiments validate this theory, demonstrating that our method not only outperforms existing LLM-as-a-judge approaches but can also surpass explicitly trained reward models. These findings suggest that the reward modeling stage can be replaced by a principled method of eliciting the knowledge already captured during pre-training, heralding a more efficient, powerful, and scalable paradigm for LLMs alignment as well as multi-modal models.

cs.CL↗

arXiv2025

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update

We study the stochastic linear bandits with heavy-tailed noise. Two principled strategies for handling heavy-tailed noise, truncation and median-of-means, have been introduced to heavy-tailed bandits. Nonetheless, these methods rely on specific noise assumptions or bandit structures, limiting their applicability to general settings. The recent work [Huang et al.2024] develops a soft truncation method via the adaptive Huber regression to address these limitations. However, their method suffers undesired computational costs: it requires storing all historical data and performing a full pass over these data at each round. In this paper, we propose a \emph{one-pass} algorithm based on the online mirror descent framework. Our method updates using only current data at each round, reducing the per-round computational cost from $\mathcal{O}(t \log T)$ to $\mathcal{O}(1)$ with respect to current round $t$ and the time horizon $T$, and achieves a near-optimal and variance-aware regret of order $\widetilde{\mathcal{O}}\big(d T^{\frac{1-ε}{2(1+ε)}} \sqrt{\sum_{t=1}^T ν_t^2} + d T^{\frac{1-ε}{2(1+ε)}}\big)$ where $d$ is the dimension and $ν_t^{1+ε}$ is the $(1+ε)$-th central moment of reward at round $t$.

cs.LG↗

arXiv2025

Learnware of Language Models: Specialized Small Language Models Can Do Big

The learnware paradigm offers a novel approach to machine learning by enabling users to reuse a set of well-trained models for tasks beyond the models' original purposes. It eliminates the need to build models from scratch, instead relying on specifications (representations of a model's capabilities) to identify and leverage the most suitable models for new tasks. While learnware has proven effective in many scenarios, its application to language models has remained largely unexplored. At the same time, large language models (LLMs) have demonstrated remarkable universal question-answering abilities, yet they face challenges in specialized scenarios due to data scarcity, privacy concerns, and high computational costs, thus more and more specialized small language models (SLMs) are being trained for specific domains. To address these limitations systematically, the learnware paradigm provides a promising solution by enabling maximum utilization of specialized SLMs, and allowing users to identify and reuse them in a collaborative and privacy-preserving manner. This paper presents a preliminary attempt to apply the learnware paradigm to language models. We simulated a learnware system comprising approximately 100 learnwares of specialized SLMs with 8B parameters, fine-tuned across finance, healthcare, and mathematics domains. Each learnware contains an SLM and a specification, which enables users to identify the most relevant models without exposing their own data. Experimental results demonstrate promising performance: by selecting one suitable learnware for each task-specific inference, the system outperforms the base SLMs on all benchmarks. Compared to LLMs, the system outperforms Qwen1.5-110B, Qwen2.5-72B, and Llama3.1-70B-Instruct by at least 14% in finance domain tasks, and surpasses Flan-PaLM-540B (ranked 7th on the Open Medical LLM Leaderboard) in medical domain tasks.

cs.LG↗

arXiv2025

A Smooth Transition Between Induction and Deduction: Fast Abductive Learning Based on Probabilistic Symbol Perception

Abductive learning (ABL) that integrates strengths of machine learning and logical reasoning to improve the learning generalization, has been recently shown effective. However, its efficiency is affected by the transition between numerical induction and symbolical deduction, leading to high computational costs in the worst-case scenario. Efforts on this issue remain to be limited. In this paper, we identified three reasons why previous optimization algorithms for ABL were not effective: insufficient utilization of prediction, symbol relationships, and accumulated experience in successful abductive processes, resulting in redundant calculations to the knowledge base. To address these challenges, we introduce an optimization algorithm named as Probabilistic Symbol Perception (PSP), which makes a smooth transition between induction and deduction and keeps the correctness of ABL unchanged. We leverage probability as a bridge and present an efficient data structure, achieving the transfer from a continuous probability sequence to discrete Boolean sequences with low computational complexity. Experiments demonstrate the promising results.

cs.LG↗

arXiv2025

Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection

Neuro-Symbolic (NeSy) AI could be regarded as an analogy to human dual-process cognition, modeling the intuitive System 1 with neural networks and the algorithmic System 2 with symbolic reasoning. However, for complex learning targets, NeSy systems often generate outputs inconsistent with domain knowledge and it is challenging to rectify them. Inspired by the human Cognitive Reflection, which promptly detects errors in our intuitive response and revises them by invoking the System 2 reasoning, we propose to improve NeSy systems by introducing Abductive Reflection (ABL-Refl) based on the Abductive Learning (ABL) framework. ABL-Refl leverages domain knowledge to abduce a reflection vector during training, which can then flag potential errors in the neural network outputs and invoke abduction to rectify them and generate consistent outputs during inference. ABL-Refl is highly efficient in contrast to previous ABL implementations. Experiments show that ABL-Refl outperforms state-of-the-art NeSy methods, achieving excellent accuracy with fewer training resources and enhanced efficiency.

cs.AI↗

arXiv2025

Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation

We study a new class of MDPs that employs multinomial logit (MNL) function approximation to ensure valid probability distributions over the state space. Despite its significant benefits, incorporating the non-linear function raises substantial challenges in both statistical and computational efficiency. The best-known result of Hwang and Oh [2023] has achieved an $\widetilde{\mathcal{O}}(κ^{-1}dH^2\sqrt{K})$ regret upper bound, where $κ$ is a problem-dependent quantity, $d$ is the feature dimension, $H$ is the episode length, and $K$ is the number of episodes. However, we observe that $κ^{-1}$ exhibits polynomial dependence on the number of reachable states, which can be as large as the state space size in the worst case and thus undermines the motivation for function approximation. Additionally, their method requires storing all historical data and the time complexity scales linearly with the episode count, which is computationally expensive. In this work, we propose a statistically efficient algorithm that achieves a regret of $\widetilde{\mathcal{O}}(dH^2\sqrt{K} + κ^{-1}d^2H^2)$, eliminating the dependence on $κ^{-1}$ in the dominant term for the first time. We then address the computational challenges by introducing an enhanced algorithm that achieves the same regret guarantee but with only constant cost. Finally, we establish the first lower bound for this problem, justifying the optimality of our results in $d$ and $K$.

cs.LG↗