AI Theory

Clipped Adam with EMA achieves optimal convergence rates for smooth and non-smooth nonconvex optimization, particularly when scales vary across different coordinates.

Certifying neural network robustness across diverse domains, this paper introduces knowledge continuity—a novel framework ensuring model stability independent of input type, norms, and distribution.

This paper introduces a computationally efficient method to approximate the optimal accuracy-fairness trade-off curve for various datasets, providing rigorous statistical guarantees and quantifying un…

This paper introduces a novel framework for evaluating the robustness of machine learning models when the true data distribution is only partially known. It defines a new risk measure (‘identifiable r…

Accelerated gradient-free optimization is achieved using only function value comparisons, significantly improving black-box optimization.

MCCFVFP, a novel Monte Carlo-based algorithm, accelerates Nash equilibrium convergence in large-scale games by combining CFR’s counterfactual value calculations with fictitious play’s best response st…

Fast imprecise oracles drastically reduce query times in matroid optimization, achieving near-optimal performance with few accurate queries.

Accelerating ERM for data-driven algorithm design using output-sensitive techniques achieves computationally efficient learning by scaling with the actual number of pieces in the dual loss function, n…

Accelerated learning in games achieved! FTXL algorithm exponentially speeds up convergence to Nash equilibria in finite N-person games, even under limited feedback.

This paper presents efficient algorithms for abductive reasoning in Logical Credal Networks (LCNs), addressing the MAP and Marginal MAP inference tasks to enable scalable solutions for complex real-wo…

Hadamard-derived Linear Binding (HLB): A novel, efficient vector symbolic architecture surpassing existing methods in classical AI tasks and deep learning applications.

This paper reveals a universal square-root growth rate for H-consistency bounds of smooth surrogate losses in classification, significantly advancing our understanding of loss function selection.

A novel post-processing framework, based on a d-dimensional generalization of the Neyman-Pearson lemma, optimally solves multi-objective learn-to-defer problems under various constraints, improving co…

This paper fully characterizes concept classes optimistically universally learnable online, introducing novel algorithms and revealing equivalences between agnostic and realizable settings.

Boosting concept bottleneck model predictability, this paper introduces a theoretical framework linking concept set properties to model performance, proposing a method for effective concept identifica…

S²GCSL: A novel scalable Granger causal structural learning approach efficiently identifies root causes of telecommunication network alarms by leveraging a linear kernel and incorporating expert knowl…

This paper introduces Bias-Conditioned Self-Influence (BCSI) for precise bias-conflicting sample detection and model rectification, enhancing fairness in machine learning.

A novel universal online learning algorithm achieves optimal gradient-variation regret across diverse function curvatures, boasting efficiency with only one gradient query per round.

A new adaptive learning rate for FTRL achieves minimax regret of O(T²/³) in online learning, improving existing best-of-both-worlds algorithms for various hard problems.

Stable oracles outperform Gaussian oracles in high-accuracy heavy-tailed sampling, overcoming limitations of Gaussian-based proximal samplers.