Paper-Conference

Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation

On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis

Provable Accelerated Convergence of Nesterov’s Momentum for Deep ReLU Neural Networks

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Strong Lottery Ticket Hypothesis with $\epilon$–perturbation

LoFT: Finding Lottery Tickets through Filter-wise Training