conftrace_

Luca Arnaboldi

3 papers · 2023–2024 · 2 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🐝 Cross-Pollinator (15)

Conferences

ICML (2) COLT (1)

Top co-authors

Florent Krzakala (3) Luca Pesce (2) Bruno Loureiro (2) Yatin Dandi (2) Ludovic Stephan (2) Emanuele Troiani (1) Lenka Zdeborová (1)

Keywords

stochastic gradient descent (1) neural network dynamics (1) gradient flow (1) mean-field limit (1) two-layer network (1) high-dimensional limit (1)

Papers

Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs ICML 2024 The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents ICML 2024 From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks COLT 2023