ICML 2026 论文列表

Constrained multi-objective reinforcement learning aims to discover a diverse set of feasible trade-offs, yet scalarization and signed, normalized group-relative advantages can be brittle under objective-scale drift, near-ties, and feasibility scarcity. We propose constrained projection policy optimization (CoPro), which alternates between an E-step moment projection and an M-step policy projection. In the E-step, we solve a Kullback-Leibler (KL)-regularized, moment-constrained projection over each sampled group to compute a nonnegative reweighting distribution ($ q^* $) that promotes feasible Pareto-front (PF) progress, preserves feasibility anchors, and suppresses ambiguous near-ties. This E-step admits a closed-form exponential-family solution and guarantees strictly positive probability mass on feasible anchors whenever feasible candidates appear in the group. In the M-step, we project the policy toward $ q^* $ via weighted maximum likelihood with a trust-region regularizer, yielding a PF-aligned update direction from comparisons without hand-crafted reward shaping. Empirically, CoPro improves feasible PF quality and robustness on constrained multi-objective benchmarks for large language model tool use and analog circuit design tasks; code is available at \href{https://anonymous.4open.science/r/CoPro-8A95/README.md}{\texttt{CoPro}}.

Reward models are central to Reinforcement Learning from Human Feedback (RLHF), especially for open-ended tasks where evaluation is inherently multi-dimensional. Recent Generative Reward Models (GRMs) improve interpretability by producing natural-language rationales and task-specific evaluation principles. However, most existing GRMs generate principles after reading the actor's response, i.e., $Q+R \rightarrow P$. We show that this coupling induces Principle Drift: when the actor performs reward hacking (e.g., verbosity, self-aggrandizement, or hallucinated self-justifications), the reward model may shift its criteria to rationalize the response, yielding inflated scores that in turn reinforce hacking during RL. We propose IP-GRM (Independent Principle GRM), a two-stage framework that first generates principles solely from the question ($Q \rightarrow P$) and then evaluates the response conditioned on $(Q, R, P)$. This decoupling keeps criteria invariant to response content, producing more objective and stable reward signals. For efficient training, we further introduce a Principle Cache strategy that reuses principles within a group, improving GRPO throughput by 23.66\% while maintaining strict intra-group consistency. In GRPO training on creative writing, IP-GRM suppresses reward hacking and improves WritingBench and CreativeWriting-v3 by up to +4.6 and +7.1 points based on Qwen3-8B, achieving state-of-the-art performance among open-source models. The model and dataset are open-sourced at https://github.com/ShadeCloak/IP-GRM.

The Densest $k$-Subgraph (D$k$S) is a fundamental combinatorial problem known for its theoretical hardness and breadth of applications. Recently, Lu et al. (AAAI 2025) introduced a penalty-based non-convex relaxation that achieves promising empirical performance; however, a rigorous theoretical understanding of its success remains unclear. In this work, we bridge this gap by providing a comprehensive theoretical analysis. We first establish the tightness of the relaxation, ensuring that the global maximum values of the original combinatorial problem and the relaxed problem coincide. Then we reveal the benign geometry of the optimization landscape by proving a strict dichotomy of stationary points: all integral stationary points are local maximizers, whereas all non-integral stationary points are strict saddles with explicit positive curvature. We propose a saddle-escaping Frank--Wolfe algorithm and prove that it achieves exact convergence to an integral local maximizer in a finite number of steps.

We study the problem of finding stationary points of non-convex functions when access to the objective is provided only through a comparison oracle that, given two points, outputs which has the larger function value. For a twice differentiable $f:\mathbb R^n\to\mathbb R$ with Lipschitz gradient and Hessian, we develop an algorithm that outputs an $\epsilon$-stationary point using $\widetilde O(n^2/\epsilon^{1.5})$ queries. Our approach uses a subroutine that estimates the normalized Hessian to accuracy $\delta$ using $\widetilde O(n^2\log(1/\delta))$ queries. We further study this problem with a quantum comparison oracle model where queries can be made in superpositions, and develop the first quantum algorithm that finds an $\epsilon$-stationary point, which takes $\widetilde O(n/\epsilon^{1.5})$ queries.

Classical optimization theory establishes that zeroth-order (ZO) algorithms suffer from a dimension-dependent slowdown, with convergence rates typically scaling with the model dimension compared to first-order methods. However, in contrast to these theoretical expectations, a growing body of recent work demonstrates the successful application of ZO methods to fine-tuning Large Language Models (LLMs) with billions of parameters. To explain this paradox, we derive the one-step learning dynamics of ZO SGD, where the empirical Neural Tangent Kernel (eNTK) naturally emerges as the key term governing the learning behavior. Inspection of the eNTK produced by ZO-SGD reveals that each element corresponds to the inner product of neural tangent vectors projected onto a random low-dimensional subspace. Thus, by invoking the Johnson-Lindenstrauss Lemma, our analysis shows that the fidelity of the ZO eNTK is governed primarily by the number of perturbations. Crucially, the approximation error depends on the model output size rather than the massive parameter dimension. This dimension-free property provides a theoretical justification for the scalability of ZO methods to LLMs finetuning tasks. We believe that this kernel-based framework offers a novel perspective for understanding ZO methods within the context of learning dynamics.

We derive algorithms for smooth nonconvex nonconcave minimax optimization and establish linear convergence rates for problems that satisfy the two-sided Polyak-Lojasiewicz (PL) inequality. At the core of our approach is the observation that Lyapunov functions can be used not only to certify convergence a posteriori, but also to design algorithms. By replacing an idealized, intractable Lyapunov function with a computable surrogate based on gradient information, we derive TALDA (Tri-Action Lyapunov Descent Ascent), a single-loop algorithm that enforces Lyapunov descent by construction. TALDA guarantees linear convergence under the two-sided PL condition, with a rate that depends explicitly on the cross-smoothness constant. This recovers existing worst-case guarantees while yielding sharper convergence rates in weakly coupled min–max problems.

Differentially private (DP) stochastic optimization algorithms are widely used in privacy-preserving deep learning, where per-sample gradient clipping and noise injection protect sensitive information. However, these operations limit existing DP algorithms to converge within a constant-radius neighborhood of the first-order stationary point, leading to solution bias and the well-known privacy-utility trade-off. To enhance model utility, we propose a novel algorithmic framework called DP-C4, which is designed to be error-Consistently-vanishing, Coupledly-clipped, solution-Calibrated, and Convergence-guaranteed. Specifically, it incorporates a carefully designed coupled clipping scheme with shifted threshold strategy, ensuring that both clipping bias and noise variance asymptotically vanish, thereby eliminating the DP-induced solution bias. Moreover, we extend existing sensitivity analysis techniques and develop a tailored privacy budget allocation to guarantee the privacy of DP-C4. Compared with the well-recognized DP-SGD, our framework injects significantly less noise under the same privacy level. In addition, we prove that our framework converges to the optimum in strongly-convex case and to a diminishing neighborhood of the first-order stationary point in non-convex case. Experiments show that DP-C4 achieves superior privacy-utility trade-off over existing baselines across various tasks and datasets.

We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of language models (LLMs) without fine-tuning model parameters. While prompt-based adaptation techniques have demonstrated the effectiveness of lightweight adaptation methods for LLMs, they typically initialize a trainable prompt or prefix with irrelevant tokens for the task at hand. In contrast, Context Tuning initializes the trainable prompt or prefix with task-specific demonstration examples, leveraging the model’s inherent In-Context Learning (ICL) ability to extract relevant information for improved few-shot learning performance. Extensive evaluations on benchmarks such as CrossFit, UnifiedQA, MMLU, BIG-Bench Hard, and ARC demonstrate that Context Tuning outperforms traditional prompt-based adaptation methods and achieves competitive accuracy with Test-Time Training at significantly higher training efficiency.

In this paper, we provide a comprehensive theoretical analysis of Stochastic Gradient Descent (SGD) and its momentum variants (Polyak Heavy-Ball and Nesterov) for tracking time-varying optima under strong convexity and smoothness. Our finite-time bounds reveal a sharp decomposition of tracking error into transient, noise-induced, and drift-induced components. This decomposition exposes a fundamental trade-off: while momentum is often used as a gradient-smoothing heuristic, under distribution shift it incurs an explicit drift-amplification penalty that diverges as the momentum parameter $\beta$ approaches 1, yielding systematic tracking lag. We complement these upper bounds with minimax lower bounds under gradient-variation constraints, proving this momentum-induced tracking penalty is not an analytical artifact but an information-theoretic barrier: in drift-dominated regimes, momentum is unavoidably worse because stale-gradient averaging forces systematic lag. Our results provide theoretical grounding for the empirical instability of momentum in dynamic settings and precisely delineate regime boundaries where vanilla SGD provably outperforms its accelerated counterparts.

The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In practice, when the number of exponential terms inside the logarithm is large or infinite, optimization becomes challenging since computing the gradient requires differentiating every term. We propose a novel convexity- and smoothness-preserving approximation to LogSumExp that can be efficiently optimized using stochastic gradient methods. This approximation is rooted in a sound modification of the KL divergence in the dual, resulting in a new $f$-divergence called the *Safe KL divergence*. Our experiments and theoretical analysis of the LogSumExp-based stochastic optimization, arising in DRO and continuous OT, demonstrate the advantages of our approach over existing baselines.

We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero almost everywhere. While existing methods address this by smoothing the differentiation process, they suffer from scalability issues, since a computationally expensive solver call is required for every gradient evaluation. To address this, we propose a decision-focused learning pipeline based on a measure transformation principle, which yields a new surrogate loss that is completely optimization-solver-free during training. We establish theoretical guarantees, including Fisher consistency and excess risk bounds. Empirically, our method achieves decision quality competitive with state-of-the-art methods while reducing training time by orders of magnitude.

By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive dynamics Jacobians and inherent training instability. While sample reuse offers a remedy for under-utilization, no prior principled framework exists, and naive attempts risks exacerbating instability. To address these challenges, we propose Reparameterization Proximal Policy Optimization (RPO). We first establish that under sample reuse, RPG naturally optimizes a PPO-style surrogate objective via Backpropagation Through Time, providing a unified framework for both on- and off-policy updates. To further ensure stability, RPO integrates a clipped policy gradient mechanism tailored for RPG and employs explicit Kullback-Leibler divergence regularization. Experimental results demonstrate that RPO maintains superior sample efficiency and consistently outperforms or achieves state-of-the-art performance across diverse tasks.

Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions and mechanisms under which non-uniform learning rates are beneficial remains limited. In this work, we investigate non-uniform learning rates through the lens of Stackelberg optimization. Specifically, we demonstrate that training neural networks with a smaller learning rate for the body layers and a larger learning rate for the final layer can be interpreted as a two-time-scale alternating gradient descent algorithm applied to a Stackelberg reformulation of the original objective. We establish finite-time convergence guarantees for the algorithm under broad conditions that accommodate constraint sets and non-smooth activation functions. Beyond convergence, we identify two mechanisms by which non-uniform learning rates can outperform uniform learning rates: (i) we show that certain problem instances induce a Stackelberg objective with stronger optimization structure than the original objective, yielding faster convergence to globally optimal solutions, (ii) our numerical analysis reveals that the Stackelberg objective can exhibit substantially sharper local curvature, especially in early training, which leads to more informative gradients and learning acceleration. Experiments in supervised learning and reinforcement learning support our findings.

Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-rank structures naturally trade off capacity and performance, existing approaches often rely on heuristic designs that ignore layer and matrix heterogeneity or require model-specific architectural modifications. We propose SALAAD, a plug-and-play framework applicable to different model architectures that induces sparse and low-rank structures during training. By formulating structured weight learning under an augmented Lagrangian framework and introducing an adaptive controller that dynamically balances the training loss and structural constraints, SALAAD preserves the stability of standard training dynamics while enabling explicit control over the evolution of effective model capacity during training. Experiments across model scales show that SALAAD substantially reduces memory consumption during deployment while achieving performance comparable to ad-hoc methods. Moreover, a single training run yields a continuous spectrum of model capacities, enabling smooth and elastic deployment across diverse memory budgets without the need for retraining.

Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general way to prevent this across different objectives. We address this issue with a unified **incentive-score decomposition** of preference optimization, revealing that different objectives share the same local update directions and differ only in their scalar weights. This decomposition provides a common framework for analyzing objectives that were previously studied in separate settings. Building on this decomposition, by analyzing the dynamics of the chosen/rejected likelihoods, we identify the **disentanglement band** (DB), a simple, testable condition that tells us when training can follow the desired path: suppress the loser while preserving the winner, possibly after an early stage. Using the DB, we propose **reward calibration** (RC), a plug‑and‑play method that adaptively rebalances the updates for chosen and rejected likelihoods to satisfy the DB, without redesigning the base objective. Empirical results show that RC leads to more disentangled dynamics, with better downstream performance observed across several settings. Our code is available at https://github.com/IceyWuu/DisentangledPreferenceOptimization.

Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning problem over a decomposed decision space, solving position-wise bandit subproblems via adaptive expert-guided sequential construction. This formulation admits regret bounds of $O(d\sqrt{T \log T})$ depending on subproblem dimensionality \(d\) rather than combinatorial space size. On standard benchmarks, our method achieves 80--98\% of specialized solvers performance while achieving two to three orders of magnitude improvement in sample and computational efficiency over Bayesian optimization methods. On real-world hardware-software co-design for AI accelerators with expensive simulations, we outperform competing methods under fixed evaluation budgets. The advantage grows with problem scale and objective count, establishing bandit optimization over decomposed decision spaces as a principled alternative to surrogate modeling or offline training for multi-objective optimization.

3D Gaussian Splatting (3DGS) enables real-time, high-fidelity view synthesis via explicit scene representations and has recently been extended to dynamic scene modeling. Despite their excellent rendering quality and interpretability, we find that explicit Dynamic GS often exhibits generalization degradation in scenes with large motion. Motivated by generalization behavior in deep neural optimization and the characteristics of Gaussian primitive optimization, we propose an update mixture strategy. This work focuses on two representative open-source explicit Dynamic GS pipelines and our approach consists of three components: (i) a space–time dependent Strictly Sparse Update with additional regularization to stabilize adaptive updates; (ii) a constant-corrected adaptive algorithm that alleviates over-scaling of primitive gradients and yields a stable mixture of adaptive and non-adaptive steps; and (iii) attributes mixing via Stochastic Attribute Averaging to mitigate frame-preference under motion disturbances. Experiments show consistent improvements and reduced generalization issues, highlighting the role of non-adaptive updates and the impact of frame-preference in explicit Dynamic GS optimization.

Graph coarsening is a fundamental dimensionality reduction technique for scaling large graphs while preserving structural and feature information. However, most existing coarsening methods are designed for static graphs and do not extend well to dynamic settings where nodes, edges, and connectivity patterns evolve over time. Recomputing a coarsened graph from scratch after every update is often infeasible, which limits scalability and real-time applicability. To address this, we propose a unified framework for coarsening discrete-time dynamic graphs by incrementally updating the coarsening mapping matrix. The framework initializes from any static coarsening technique and then efficiently incorporates real-world graph events, including node additions, node deletions, and edge modifications. We instantiate this framework with two optimization based incremental update algorithms tailored to different dynamic regimes, one focusing on efficiently integrating growth related changes and another handling broader topology evolution with adaptive reassignment. We derive fast and scalable solvers with convergence guarantees, and provide theoretical guarantee via $\epsilon$-similarity bounds that quantify and control quality degradation in the coarsened graph. Extensive experiments under realistic dynamic scenarios show substantial improvements in runtime and memory, delivering significant speedups while maintaining or improving downstream task performance, including graph neural network accuracy.

This paper deals with stochastic optimization problems involving Markovian noise with a zero-order oracle. We present and analyze a novel derivative-free method for solving such problems in strongly convex smooth and non-smooth settings with both one-point and two-point feedback oracles. Using a randomized batching scheme, we show that when mixing time $\tau$ of the underlying noise sequence is less than the dimension of the problem $d$, the convergence estimates of our method do not depend on $\tau$. This observation provides an efficient way to interact with Markovian stochasticity: instead of invoking the expensive first-order oracle, one should use the zero-order oracle. Finally, we complement our upper bounds with the corresponding lower bounds. This confirms the optimality of our results.