Machine Learning

ARC: a novel generalist graph anomaly detector leveraging in-context learning for efficient, one-for-all anomaly detection across various datasets without retraining.

This paper unveils the Transformer’s approximation power, deriving explicit Jackson-type rates to reveal its strengths and limitations in handling various sequential relationships.

This paper presents novel algorithms for approximating Pareto-optimal solutions to bi-objective k-clustering problems, achieving provable approximation guarantees and demonstrating effectiveness throu…

Boosting meta-learning, this paper introduces a novel, flexible approach to create approximately equivariant neural processes that outperform both non-equivariant and strictly equivariant counterparts…

ANT: An adaptive noise schedule automatically determines optimal noise schedules for time series diffusion models, significantly boosting performance across diverse tasks.

Corrected graph convolutions prevent oversmoothing and exponentially improve GNN classification accuracy.

This work introduces PDOA, an offline adaptation framework for constrained multi-objective RL, using demonstrations instead of manually designed preferences to infer optimal policies while satisfying …

This paper uses information theory to improve conformal prediction, proving new ways to bound uncertainty and creating better training methods and side-information incorporation.

Improved Empirical Fisher (iEF) approximation significantly boosts the performance of Natural Gradient Descent (NGD) optimizers, offering superior convergence and generalization.

A novel multilinear model analytically explains the emergence and scaling laws of skills in the multitask sparse parity problem, accurately predicting skill emergence in neural networks.

Mecoin: a novel memory module for efficient graph few-shot class-incremental learning, tackles catastrophic forgetting by employing structured memory units and a memory representation adaptation modul…

This paper provides novel theoretical analyses of utility functions in MORL, characterizing preferences and functions guaranteeing optimal policies.

Adaptive algorithm achieves tight regret bounds for infinitely many-armed bandits under generalized rotting constraints, addressing the challenge of decreasing rewards over time.

Accelerated Gradient Method for Bilevel Optimization (AGM-BiO) achieves state-of-the-art convergence rates for simple bilevel optimization problems, requiring fewer iterations than existing methods to…

AccBO: A new accelerated algorithm achieves O(ε⁻³) oracle complexity for stochastic bilevel optimization with unbounded smoothness, significantly improving upon existing O(ε⁻⁴) methods.

Amortized sampling from complex posteriors using diffusion models is achieved via a novel data-free learning objective, Relative Trajectory Balance (RTB). RTB’s asymptotic correctness is proven, offe…

Large-scale transformers achieve grandmaster-level chess play via supervised learning on a new 10M game benchmark dataset, demonstrating impressive generalization beyond memorization.

Amortized Fourier Neural Operators (AM-FNOs) dramatically improve efficiency in solving PDEs by using neural networks for kernel parameterization, achieving up to 31% better accuracy compared to exist…

Amortized Decision-Aware BED prioritizes maximizing downstream decision utility by instantly proposing informative experimental designs and inferring decisions, facilitating accurate decision-making.

CAASL: An amortized active intervention design policy trained via reinforcement learning, enabling adaptive, real-time causal graph inference without likelihood access.