This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.

The paper establishes information-theoretic lower bounds for stochastic optimization using low-bit gradients by reducing the problem to compressed Gaussian mean estimation, yielding sharp bounds on co…

This paper settles the complexity of three sketching problems in graphs and distributions.

The paper introduces novel, efficient differentially private algorithms for estimating monotone statistics, significantly improving sample complexity compared to existing methods.

The paper addresses the failure of fixed-price inference in resource-constrained pricing controllers by developing a target-aware controller that tracks local densities and provides certified, shrinki…

The paper introduces an optimal black-box auditing framework using Donsker-Varadhan estimators to estimate Rényi differential privacy (RDP) guarantees for machine learning algorithms.

The paper establishes new hardness amplification results for Learning Parity with Noise (LPN) and its sparse variants, showing that solving the problem on a small fraction of instances implies solving…

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifie…

The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure…

This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…

The paper presents a new worst-case to average-case reduction for the Learning Parity with Noise (LPN) problem, achieving hardness for inverse-polynomial noise rates previously unattainable.

The paper introduces Fine-Tuning Integrity (FTI), a security goal that uses Succinct Model Difference Proofs (SMDPs) to cryptographically prove that a fine-tuned model update adheres to specific struc…

CSULoRA is a post-hoc method that corrects trained LoRA adapters by estimating a safety-aligned subspace and solving a penalized minimum-change problem to attenuate unsafe update directions while pres…

The paper introduces a new anytime-valid inference method to correct split selection in online decision trees, providing robust statistical guarantees for streaming data that existing methods lack.

The paper introduces Regularized Large Neighborhood Search (RLNS), a method that adapts the LNS heuristic into an efficient MCMC sampler for combinatorial optimization, allowing end-to-end learning wi…

The paper demonstrates that extrapolative weight averaging can effectively navigate and extend the correctness-efficiency frontier in code RL, leading to improved performance on complex programming ta…

The paper presents two new attacks on decisional $k$-sparse LWE and LPN problems for higher moduli $q$ by generalizing the Kikuchi method using graph theory.

The paper introduces the PML envelope, a novel definition that provides a robust and operationally meaningful measure of information leakage about a secret, satisfying both post-processing robustness…

The paper characterizes the optimal achievable rate for differentially private hypothesis testing using e-values, providing an exact algorithm for both fixed and sequential settings.