๐ข Rensselaer Polytechnic Institute
Towards Exact Gradient-based Training on Analog In-memory Computing
ยท1654 wordsยท8 minsยท
loading
ยท
loading
Machine Learning
Deep Learning
๐ข 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 โฆ
Linear Causal Bandits: Unknown Graph and Soft Interventions
ยท1964 wordsยท10 minsยท
loading
ยท
loading
AI Theory
Causality
๐ข Rensselaer Polytechnic Institute
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 Flexible Framework for Preference-Guided Multi-Objective Learning
ยท2495 wordsยท12 minsยท
loading
ยท
loading
AI Theory
Optimization
๐ข Rensselaer Polytechnic Institute
FERERO, a novel framework, tackles multi-objective learning by efficiently finding preference-guided Pareto solutions using flexible preference modeling and convergent algorithms.
Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
ยท3172 wordsยท15 minsยท
loading
ยท
loading
AI Generated
Machine Learning
Self-Supervised Learning
๐ข Rensselaer Polytechnic Institute
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-shoโฆ
A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
ยท2217 wordsยท11 minsยท
loading
ยท
loading
AI Theory
Optimization
๐ข Rensselaer Polytechnic Institute
BLOCC, a novel first-order algorithm, efficiently solves bilevel optimization problems with coupled constraints, offering improved scalability and convergence for machine learning applications.