NeurIPS 2026 Papers

Multi-objective Bayesian optimization (MOBO) is commonly approached through specialized acquisition functions or scalarization schemes designed to explicitly account for trade-offs among non-preferential objectives. In this work, we show that such complexity might be unnecessary. We propose a framework that extends standard single-objective acquisition functions directly to the multi-objective setting through a hypervolume-based transformation. We further extend hedge strategies for acquisition functions, which are typically used only in single-objective optimization, to the multi-objective regime. Our approach requires minimal modification to existing Bayesian optimization pipelines and avoids the need for bespoke multi-objective formulations. We demonstrate how a broad class of commonly used single-objective acquisition functions and hedge strategies can be adapted in a principled manner to handle multiple objectives, while preserving their intuitive interpretation and computational efficiency. Empirically, we evaluate the proposed methods across a range of synthetic and real-world multi-objective benchmarks. Despite their simplicity, our extensions consistently match or outperform more complex state-of-the-art MOBO methods in terms of optimization performance and sample efficiency. These results suggest that effective multi-objective Bayesian optimization can be achieved by reusing and carefully extending well-established single-objective acquisition strategies, offering a simpler and more flexible alternative to existing approaches.

Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learning remains challenging. Population-based, gradient-free optimization circumvents backpropagation through non-differentiable spike dynamics by estimating gradients. However, with finite populations, high variance of these estimates can induce harmful and overly aggressive update steps. Inspired by trust-region methods in reinforcement learning that constrain policy updates in distribution space, we propose **Signal-Adaptive Trust Regions (SATR)**, a distributional update rule that constrains relative change by bounding KL divergence normalized by an estimated signal energy. SATR automatically expands the trust region under strong signals and contracts it when updates are noise-dominated. We instantiate SATR for Bernoulli connectivity distributions, which have shown strong empirical performance for RSNN optimization. Across a suite of high-dimensional continuous-control benchmarks, SATR improves stability under limited populations and reaches competitive returns against strong baselines including PPO-LSTM. In addition, to make SATR practical at scale, we introduce a bitset implementation for binary spiking and binary weights, substantially reducing wall-clock training time and enabling fast RSNN policy search.

While adaptive gradient methods are the workhorse of modern machine learning, sign-based optimization algorithms such as Lion and Muon have recently demonstrated superior empirical performance over AdamW in training large language models (LLM). However, a theoretical understanding of why sign-based updates outperform variance-adapted methods remains elusive. In this paper, we aim to bridge the gap between theory and practice through the lens of heavy-tailed gradient noise, a phenomenon frequently observed in language modeling tasks. Theoretically, we introduce a novel generalized heavy-tailed noise condition that captures the behavior of LLMs more accurately than standard finite variance assumptions. Under this noise model, we establish sharp convergence rates of SignSGD and Lion for generalized smooth function classes, matching or surpassing previous best-known bounds. Furthermore, we extend our analysis to Muon and Muonlight, providing what is, to our knowledge, the first rigorous analysis of matrix optimization under heavy-tailed stochasticity. These results offer a strong theoretical justification for the empirical superiority of sign-based optimizers, showcasing that they are naturally suited to handle the noisy gradients associated with heavy tails. Empirically, LLM pretraining experiments validate our theoretical insights and confirm that our proposed noise models are well-aligned with practice.

Existing guarantees for misspecified kernelized bandit optimization pay for misspecification through kernel complexity: in generic offline bounds, the misspecification level $\varepsilon$ is multiplied by $\sqrt{d_\mathrm{eff}}$, where $d_\mathrm{eff}$ is the kernel effective dimension, while in online regret bounds, the corresponding penalty is $\sqrt{\gamma_n}\,n\varepsilon$, where $\gamma_n$ is the maximum information gain after $n$ rounds of interaction. In this work, we show that, for a large class of kernels, the misspecification amplification can be reduced to logarithmic or polylogarithmic growth. In the offline setting, we first prove high-probability simple-regret bounds whose misspecification term is governed by a spectral Lebesgue constant. This yields logarithmic amplification for one-dimensional monotone spectra and polylogarithmic amplification for multivariate Fourier-diagonal product kernels. In the online setting, we modify a domain-splitting algorithm and prove a cumulative regret bound of $\widetilde{\mathcal O}(\sqrt{\gamma_n n}+n\varepsilon)$ under mild localized eigendecay assumptions, removing the extra $\sqrt{\gamma_n}$ factor from the misspecification term. The common principle is localization: spectral localization controls the Lebesgue constant of the offline approximation operator, while domain splitting implements the spatial analogue of this mechanism in the online setting, preventing local misspecification errors from being amplified globally.

Reinforcement learning with verifiable rewards (RLVR) enables large language models (LLMs) to continuously self-improve their reasoning capabilities. Compared to RLVR's scalar rewards, recent self-supervised on-policy distillation methods leverage denser supervision signals. However, both paradigms suffer from exploration bottlenecks, struggling to escape local optima when the policy fails to sample valid solutions. Relying on external demonstrations can bypass this issue; however, the off-policy nature hinders genuine self-improvement and the mismatched-distribution reasoning can not be fully exploited. In this work, we propose Self-Evolution Policy Optimization (SEPO), a framework that drives continuous reasoning capability evolution via guided exploration and in-distribution exploitation. Specifically, SEPO utilizes labels to elicit correct reasoning from the policy, unlocking the exploration potential. By treating current policy conditioned on this in-distribution reasoning as a self-teacher, SEPO distills the newly discovered solution back into the policy. Through this iterative cycle of policy-intrinsic exploration and exploitation, SEPO achieves robust and continuous capability evolution. Across scientific, tool-use, and complex logical reasoning domains, SEPO consistently achieves the best performance under identical training time or steps, demonstrating superior efficiency and convergence ceilings. Notably, SEPO maintains stable improvements even in scenarios where baselines severely underperform or fail entirely, such as on complex tasks or with small-scale models.

We study optimistic bilevel optimization when the lower-level problem has a non-isolated manifold of minimizers. In this setting, the hyper-objective may be non-differentiable because the upper-level criterion must choose among multiple lower-level solutions. Under a local Polyak--{\L}ojasiewicz (P{\L}) condition, we show that differentiability does not require the lower-level solution set to be a singleton: uniqueness of the optimistic selection is sufficient. This yields an explicit pseudoinverse-based hyper-gradient formula extending the classical singleton-minimizer result. We further characterize the regularity of the hyper-objective: non-degeneracy of the selected minimizer along the solution manifold yields local smoothness, while failure of uniqueness can create many non-differentiable points and failure of non-degeneracy can destroy all positive H\"older regularity of the hyper-gradient. Motivated by this theory, we propose HG-MS, a select-then-differentiate method combining explicit optimistic selection with efficient pseudoinverse-based hyper-gradient computation. Despite the nonconvex nature of optimistic selection over the lower-level solution manifold, we show that HG-MS converges to a stationary point of the optimistic objective with complexity governed by the intrinsic dimension of the solution manifold rather than its ambient dimension. Empirically, we test a practical variant of HG-MS for matched-budget LLM source reweighting. This variant preserves the select-then-differentiate principle and obtains the best GSM8K/MATH scores across the tested backbones, along with competitive or best MT-Bench instruction-following results.

Generative models are increasingly central to many de novo discovery pipelines, in which designs are generated at scale and filtered through virtual screens to determine a set of candidates to experimentally validate. While Bayesian optimization (BO) is a natural fit for this setting, as it uses past evaluations to guide future proposals, the computational overhead required for its sequential decision-making becomes a bottleneck when virtual screens are relatively cheap. We make BO practical in this regime by exploiting the unique combination of a linear model constrained to a spherical domain where high-dimensional latents concentrate. We build off recent work justifying the use of linear surrogates, while deriving nearly closed-form solutions to the surrogate modelling and acquisition problems that exploit spherical symmetry. The result is a $100\times$ speedup over state-of-the-art baselines, with matching or improved performance across molecular and image generation benchmarks. Altogether, our method makes BO a practical drop-in for de novo pipelines where it was previously too slow to consider.

We present a hypernetwork that generates the parameters of an implicit neural representation (INR) for a given signal in a single forward pass, without test-time optimization. Existing hypernetworks for this problem either ignore the chain-rule structure of the test-time optimization that produces an INR or, when they preserve it, instantiate the structure with MLPs whose parameter count grows quartically in target-network width. Our central contribution is to show that this parameter-count cost is structural to the MLP instantiation, not to the optimization-oriented principle of preserving chain-rule structure, and to resolve it by replacing the MLP body with attention. The resulting hypernetwork combines three design choices: an output-neuron-centric tokenization that aligns the token axis with each layer's output-neuron axis; an information-flow consistency rule that fixes the role of every cross-attention module from the representation its output should occupy; and a token-space iterative rollout that realizes the five quantities one optimization step on the target INR computes as five cross-attention modules with parameter count independent of target-network width. Across five 2D and 3D INR generation benchmarks, our method outperforms the state-of-the-art single-pass and optimization-oriented baselines; scales to target-network widths at which the MLP-based optimization-oriented paradigm exhausts GPU memory; and produces the highest result on NeRF generation without ground-truth INR weights supervision.

In centralized, distributed, and federated learning with stochastic gradients and $n$ workers, it was recently shown that it is infeasible to find an $\varepsilon$-stationary point faster than $\tilde{\Omega}(\min[{\frac{d \kappa L \Delta}{\varepsilon}} + \frac{h L \Delta}{\varepsilon} + \frac{h \sigma^2 L \Delta}{n \varepsilon^2}, {\frac{h \sigma^2 L \Delta}{\varepsilon^2}} + \frac{h L \Delta}{\varepsilon}])$ seconds in both homogeneous and heterogeneous settings under standard assumptions: $L$-smoothness, $\sigma^2$-bounded unbiased stochastic gradients, and lower boundedness of the function, i.e., $f(x) \geq f^\star$ for all $x \in \mathbb{R}^d$, where $\Delta = f(x^0) - f^*$, $h$ is the computation time, $\kappa$ is the communication speed between the workers and the server, and $d$ is the dimension of the iterates and gradients. This result is pessimistic since it does not allow a complexity in which both ${\frac{d \kappa L \Delta}{\varepsilon}}$ and ${\frac{h \sigma^2 L \Delta}{\varepsilon^2}}$ improve with $n$, even when using random sparsification techniques; moreover, this lower bound can be matched by either non-distributed SGD or vanilla Synchronous SGD, which reduces the impact of recent progress in the design of compression-based methods. In this work, we challenge this limitation and propose new compressed methods, Inkheart SGD and M4, and show that under an additional structural assumption, which is necessary due to the lower bound and which does not restrict the class of considered problems, we achieve new state-of-the-art time complexities that break this pessimistic barrier and allow scaling with the number of workers $n$.

We study zeroth-order optimization where solutions must minimize a cost $d(s)$ while maintaining high probability under a complex generative prior $\mathcal{L}(s)$ (e.g., a parameterized model). This reduces to sampling from a target distribution proportional to $\mathcal{L}(s) e^{-T \cdot d(s)}$. Since classical model-based optimization (MBO) lacks finite-sample guarantees for expressive approximate learners, we introduce \emph{coarse learnability}, a flexible statistical assumption requiring only that a learned model covers the target's probability mass within a polynomial factor. Leveraging this assumption, we design an iterative MBO algorithm called ALDRIFT with a sample correction step that provably approximates the target using only a polynomial number of samples. We apply this framework to globally optimizing non-convex objectives bounded by a quadratic envelope in $\mathbb{R}^d$, where we show this assumption is naturally satisfied for a family of ``optimistic'' posterior distributions. To reach global $\varepsilon$-optimality, this implies a sample complexity of $\widetilde{O}(\log 1/\varepsilon)$, a rate characteristic of optimistic space-partitioning methods. We further justify coarse learnability as an assumption for generative priors theoretically, proving that in simple settings, parametric maximum likelihood estimation and over-smoothed kernel density estimators naturally satisfy it. Finally, one motivation for our framework comes from inference-time alignment. Though our primary contribution is formalizing the theoretical foundations of MBO, we provide qualitative evidence that, in simple settings, even primitive LLMs can shift their distributions toward lower-cost regions when fine-tuned with zeroth-order feedback.

We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect to the corresponding continuous optimization problem. We show that integer optimization can sometimes require strictly more samples and sometimes strictly smaller number of samples, depending on the structure of the objective and constraints. 1. For Lipschitz objectives over subsets of the $\ell_\infty$ ball, the statistical complexity of general stochastic mixed-integer, nonlinear, nonconvex optimization is exactly the same as stochastic linear optimization with just bound constraints. 2. For Lipschitz objectives over subsets of the $\ell_2$ ball, we show that integer optimization can require strictly *smaller* sample size compared to the continuous setting in a certain regime. To get to this result, we also establish tight sample complexity results for nonconvex continuous stochastic optimization which, to the best of our knowledge, do not appear in prior work. 3. For strongly convex, smooth objectives, integer optimization has high statistical complexity compared to the continuous setting. In particular, we show that integer optimization requires $\Omega(1/\epsilon^2)$ samples to report an $\epsilon$-approximate solution, compared to the well-known $O(1/\epsilon)$ sample complexity from the continuous optimization literature.

Software performance optimization is a notoriously complex and manual task. Despite the growing use of Large Language Models (LLMs) for code refinement, we still lack benchmarks that capture how optimization actually happens in real-world codebases. Existing frameworks often oversimplify the problem by focusing on isolated functions or a single performance metric, missing the critical trade-offs between execution time and memory footprint, the inherent noise of the measurement environment, and the variability introduced by different input data and execution conditions. We address this by introducing SWE-Pro, a repository-level benchmark derived from 102 expert-written optimizations from open-source projects. Unlike previous benchmarks, SWE-Pro pairs each task with parameterized tests to evaluate runtime, peak memory, and Time-Weighted Memory Usage (TWMU) varying input data and execution conditions under noise-aware measurement conditions. Our evaluation shows that current LLMs struggle significantly: runtime gains are negligible, and memory optimizations are nearly non-existent. This stands in sharp contrast to expert implementations, which achieve an aggregate speedup of 15.5x and peak memory reduction of 171.3x over benchmark tasks. Expert-written improvements are observed in 91.2% of tasks for runtime and 65.7% for peak memory. Our findings expose a substantial gap between current LLMs capabilities and the demands of expert-level engineering.

Multi-objective optimization aims to solve problems with competing objectives. Evaluating such problems is often slow or expensive, limiting the budget of evaluations. In many applications, historical data from related optimization tasks is available and can be leveraged via meta-learning to accelerate optimization. Bayesian optimization, as a promising technique for expensive black-box problems, has been extended independently to meta-learning and multi-objective optimization, but methods that simultaneously address both settings remain largely unexplored. We propose SMOG—a scalable and modular meta-learning model based on a multi-output Gaussian process—that explicitly learns correlations between objectives. SMOG builds a structured joint Gaussian process prior across meta- and target tasks and, after conditioning on metadata, yields a closed-form prior for the target task. This construction propagates metadata uncertainty into the target surrogate in a principled way. SMOG supports hierarchical, parallel training, achieving linear scaling with the number of meta-tasks. The resulting surrogate integrates seamlessly with standard multi-objective Bayesian optimization acquisition functions. We demonstrate that our method is consistently competitive, delivering strong data efficiency across representative benchmarks and applications.

Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for each query. Existing trainable methods usually rely on a lightweight selector to score context units followed by a hard Top-$K$ selection, which blocks gradients from the language modeling loss. As a result, these methods commonly resort to distilling layer-wise dense attention distributions. While this approach encourages the selector to rank context units according to dense attention weights in the original model, such a ranking is not directly aligned with their impact on the model's final predictions under a fixed attention budget (ie, the number of attended context units per query), which can waste the limited attention budget on less useful units. To address this ranking misalignment, we propose **S**imple **A**ttention **S**parsification (SAS), a gated sparse attention mechanism that optimizes context ranking end-to-end with the language modeling loss. The key idea is to inject the selector's continuous scores into the attention logits during training, allowing the language modeling loss to update the selector through standard backpropagation. We identify several choices that are crucial to make this simple design work well in practice: placing the gate inside the attention $\operatorname{softmax}$ in log form, keeping all context units active during training so each of them can receive gradients, and preserving continuous selector scores so the model learns relative priorities rather than only hard selections. Since a naive implementation that explicitly materializes the full attention matrix would cause prohibitive memory overhead for long sequences, we implement a memory-efficient Triton kernel that integrates the design into a FlashAttention-style computation. SAS consistently outperforms trainable sparse-attention across attention budgets, with especially large accuracy gains under tight budgets, demonstrating more effective context ranking for downstream tasks.

Chemical reaction-condition optimization --- choosing the catalyst, ligand, solvent, reagent, temperature, time, and atmosphere that jointly maximize yield and stereoselectivity --- is a central, judgement-laden subtask of organic methodology research that large language models are increasingly expected to support. Yet existing chemistry benchmarks evaluate reaction-class labelling, retrosynthesis, or SMILES manipulation, and do not ask models to read a real condition-screening table and pick the best set. We introduce RxnOptBench, a benchmark whose every option and precedent is a real wet-lab entry mined from the optimization tables of organic-methodology papers published in 2025, graded by a continuous relative score that fuses yield with stereoselectivity (ee, dr, rr) so near-correct answers are not collapsed to zero, and equipped with a paired precedents-vs-no-precedents design that isolates in-context use of literature evidence from parametric memorization. Across nine frontier LLMs and three Chemistry LLMs, even the best models leave substantial headroom: chemistry-specialized models fall to the random-baseline floor on multi-axis selection, while open-weight models have closed most of the gap to proprietary frontier models. We release the benchmark, the human-verified extraction pipeline, and the inference and evaluation code.

LLMs are commonly trained through multi-stage post-training: first via RLHF, then fine-tuned for other downstream objectives. Yet even small downstream updates can compromise earlier learned behaviors (e.g., safety), exposing a brittleness known as catastrophic forgetting. This suggests standard RLHF objectives do not guarantee robustness to future adaptation. To address it, most prior work designs downstream-time methods to preserve previously learned behaviors. We argue that preventing this requires pre-finetuning robustness: the base policy should avoid brittle high-reward solutions whose reward drops sharply under fine-tuning. We propose Fine-tuning Robust Policy Optimization (FRPO), a robust RLHF framework that optimizes reward not only at the current policy, but across a KL-bounded neighborhood of policies reachable by downstream adaptation. The key idea is to ensure reward stability under policy shifts via a max-min formulation. By modifying GRPO, we develop an algorithm with no extra computation, and empirically show it substantially reduces safety degradation across multiple base models and downstream fine-tuning regimes (SFT and RL) while preserving downstream task performance. We further study a math-focused RL setting, demonstrating that FRPO preserves accuracy under subsequent fine-tuning.

We study noisy inductive matrix completion (IMC) in the presence of heavy-tailed and possibly asymmetric noise, where the goal is to recover a rank-$r$ matrix of ambient dimension $d$ given $n$ features as side prior information. So far, there has been a lack of theoretical understanding of the statistical estimation error in noisy IMC, let alone theory under heavy-tailed noise. We first develop an efficient two-stage nonconvex algorithm, called RGDIMC, via robust gradient descent with spectral initialization and feature-aware matrix factorization, based on an adaptive Huber loss to accommodate heavy-tailed noise. We prove that RGDIMC converges locally at a linear rate with sample complexity depending only linearly on $n$ (up to $\log n$) and logarithmically on $d$, and achieves the minimax-optimal statistical error rate $O_p(\sigma\sqrt{dr/p})$ under merely a bounded second-moment condition on the noise, where $r$ is the rank of the unknown core matrix. The theoretical results are strongly supported by extensive experiments.

Latent space Bayesian optimization circumvents the curse of dimensionality over structured inputs by performing Gaussian process surrogate-guided search in a continuous latent space learned by deep generative models. However, existing latent space Bayesian optimization methods overlook both the inherent stochasticity of latent space representations and the geometric properties of the manifold induced by VAE, leading to suboptimal optimization performance. In this work, we propose a marginalized kernel that integrates out the latent variables through the VAE inference posterior, yielding a closed-form kernel on the observation space that naturally accounts for encoding uncertainty. We adopt a quadratic polynomial kernel as the base kernel in the latent space, which captures discrepancies in the first two moments of the latent posteriors while avoiding the bandwidth sensitivity inherent to the RBF kernel. Furthermore, inspired by the Riemannian interpretation of VAEs, we incorporate a geometry-aware sampling scheme that leverages the metric structure revealed by the learned posterior covariances to guide candidate acquisition toward high-information regions of the latent space. Empirical evaluations on molecular design and robot design tasks demonstrate that our method outperforms existing state-of-the-art baselines across the majority of tasks.

A core challenge in structural biophysics is generating biomolecular conformations that are both physically plausible and consistent with experimental measurements. While sequence-to-structure diffusion models provide powerful priors, posterior sampling methods steer generation by perturbing atomic coordinates with gradients from experimental likelihoods. However, when the target lies in a low-density region of the prior, these methods require aggressive upweighting of the likelihood that can destabilize sampling and be sensitive to hyperparameters. We propose EmbedOpt, an inference-time steering framework that introduces an orthogonal optimization axis: rather than performing posterior sampling under a fixed prior, EmbedOpt directly optimizes the prior by updating the model's conditional embedding. This embedding space encodes rich coevolutionary signals, so optimizing it shifts the structural prior to align with experimental constraints. Empirically, EmbedOpt matches coordinate-based posterior sampling baselines on sparse distance constraints and outperforms them on cryo-electron microscopy map fitting, including real, noisy experimental ones. Furthermore, EmbedOpt's smooth optimization behavior yields robustness to hyperparameters spanning two orders of magnitude and enables comparable performance with fewer diffusion steps.