🏢 Rensselaer Polytechnic Institute

Analog in-memory computing (AIMC) training suffers from asymptotic errors due to asymmetric updates. This paper rigorously proves this limitation, proposes a novel discrete-time model to characterize …

Causal bandits with unknown graphs and soft interventions are solved by establishing novel upper and lower regret bounds, plus a computationally efficient algorithm.

FERERO, a novel framework, tackles multi-objective learning by efficiently finding preference-guided Pareto solutions using flexible preference modeling and convergent algorithms.

VQShape: a pre-trained model uses abstracted shapes as interpretable tokens for generalizable time-series classification, achieving comparable performance to black-box models and excelling in zero-sho…

BLOCC, a novel first-order algorithm, efficiently solves bilevel optimization problems with coupled constraints, offering improved scalability and convergence for machine learning applications.