Poster

DropCov: A Simple yet Effective Method for Improving Deep Architectures
Qilong Wang · Mingze Gao · Zhaolin Zhang · Jiangtao Xie · Peihua Li · Qinghua Hu

Poster

Tue 14:00

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods
Randall Balestriero · Yann LeCun

Poster

Tue 14:00

A Spectral Approach to Item Response Theory
Duc Nguyen · Anderson Ye Zhang

Poster

Wed 9:00

Globally Gated Deep Linear Networks
Qianyi Li · Haim Sompolinsky

Workshop

Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
Diyuan Wu · Vyacheslav Kungurtsev · Marco Mondelli

Poster

Thu 14:00

The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?
Jean Barbier · TianQi Hou · Marco Mondelli · Manuel Saenz

Poster

Wed 14:00

Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality
Ilyas Fatkhullin · Jalal Etesami · Niao He · Negar Kiyavash

Poster

Wed 9:00

A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate
Slavomír Hanzely · Dmitry Kamzolov · Dmitry Pasechnyuk · Alexander Gasnikov · Peter Richtarik · Martin Takac

Workshop

From Local to Global: Spectral-Inspired Graph Neural Networks
Ningyuan Huang · Soledad Villar · Carey E Priebe · Da Zheng · Chengyue Huang · Lin Yang · Vladimir Braverman

9 Results