Thomas Robert

4 papers · 2018–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🚀 Conference Pioneer

Venues

ECCV (2) ICLR (1) NeurIPS (1)

Top co-authors

Matthieu Cord (2) Mher Safaryan (2) Dan Alistarh (2) Ionut-Vlad Modoranu (2) Peter Richtarik (1) Arthur Douillard (1) Grigory Malinovsky (1) Eduardo Valle (1) Nicolas Thome (1) Charles Ollion (1)

Research topics

Machine Learning (2) Optimization & Theory · Machine Learning (2) Deep Learning (1) Mathematics & Optimization (1) Application Areas (1) Optimization (1) Optimization & Theory · Deep Learning (1)

Keywords

adaptive optimization (2) memory efficiency (2) neural network optimization (1) convergence guarantee (1) gradient compression (1) adam optimizer (1) error feedback (1) adaptive optimizer (1) neural network (1) low-rank projection (1) language model training (1) gradient statistics (1) distributed optimization (1)

Papers

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics ICLR 2025 MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence NeurIPS 2024 PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning ECCV 2020 HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning ECCV 2018