🏢 University of Chicago

Learned dynamical systems often fail to capture true physical behavior; this work introduces an ergodic theoretic approach to improve statistical accuracy by incorporating Jacobian information during …

Unlocking the optimal variance estimation rate in compound decision theory under bounded means, this paper reveals a surprising (log log n/log n)² rate and introduces a rate-optimal cumulant-based est…

VISPA, a novel BNN training framework using Gaussian variational inference and low-rank SDP, achieves state-of-the-art accuracy on various benchmarks.

Schur Nets boost higher-order GNNs by efficiently exploiting local graph structure for automorphism equivariance, achieving improved performance without the computational burden of traditional methods…

S-SOS: A new algorithm solves complex, parameterized polynomial problems with provable convergence, enabling efficient solutions for high-dimensional applications like sensor network localization.

Ridgeless regression, surprisingly, generalizes well even with noisy data if dimension scales sub-polynomially with sample size.

Optimal algorithms for learning partitions are designed, achieving minimum query complexity even with up to l faulty oracle responses.

This paper develops novel finite-sample bounds for off-policy linear treatment effect estimation with adaptively collected data, proposing online learning algorithms to improve estimation accuracy and…

A novel data-driven relighting model achieves state-of-the-art accuracy by learning latent intrinsic and extrinsic scene properties, even recovering albedo without explicit supervision.

AGENTPOISON: A novel backdoor attack compromises LLM agents by poisoning their memory or knowledge bases, achieving high success rates with minimal performance impact.