Michael Eli Sander

6 papers · 2023–2025 · 2 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (15) ❓ The Questioner

Conferences

ICML (4) ICLR (2)

Top co-authors

Mathieu Blondel (4) Gabriel Peyré (3) Vincent Roulet (2) Tianlin Liu (2) Yu-Han Wu (1) Gérard Biau (1) Raja Giryes (1) Joan Puigcerver (1) Josip Djolonga (1) Taiji Suzuki (1)

Keywords

neural network pruning (1) convex optimization (1) linear programming (1) differentiable programming (1) sparse model (1) sparse mixture of expert (1) top-k selection (1) isotonic optimization (1) differentiable top-k (1)

Papers

Towards Understanding the Universality of Transformers for Next-Token Prediction ICLR 2025

Loss Functions and Operators Generated by f-Divergences ICML 2025

Joint Learning of Energy-based Models and their Partition Function ICML 2025

Implicit regularization of deep residual networks towards neural ODEs ICLR 2024

How do Transformers Perform In-Context Autoregressive Learning ? ICML 2024

Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective ICML 2023