|
Affinity Event
|
|
Enhancing Communication Efficiency and Robustness in Split-Federated Learning with Rate-Distortion inspired Compression
Chamani Shiranthika Jayakody Kankanamalage · Hadi Hadizadeh · Ivan Bajić · Parvaneh Saeedi
|
|
|
Workshop
|
Sun 11:14
|
Muxing Wang, Pengkun Yang & Lili Su. On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments
|
|
|
Workshop
|
|
On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments
Muxing Wang · Pengkun Yang · Lili Su
|
|
|
Poster
|
Thu 16:30
|
Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training
Atli Kosson · Bettina Messmer · Martin Jaggi
|
|
|
Poster
|
Thu 11:00
|
Universal Rates for Active Learning
Steve Hanneke · Amin Karbasi · Shay Moran · Grigoris Velegkas
|
|
|
Poster
|
Wed 16:30
|
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
Dayal Singh Kalra · Maissam Barkeshli
|
|
|
Poster
|
Fri 16:30
|
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
Taira Tsuchiya · Shinji Ito
|
|
|
Workshop
|
|
On Your Mark, Get Set, Warmup!
Dayal Singh Kalra · Maissam Barkeshli
|
|
|
Poster
|
Fri 11:00
|
An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
Yunzhe Hu · Difan Zou · Dong Xu
|
|
|
Poster
|
Fri 11:00
|
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
Deqing Fu · Tian-qi Chen · Robin Jia · Vatsal Sharan
|
|
|
Poster
|
Thu 11:00
|
Stepping on the Edge: Curvature Aware Learning Rate Tuners
Vincent Roulet · Atish Agarwala · Jean-Bastien Grill · Grzegorz Swirszcz · Mathieu Blondel · Fabian Pedregosa
|
|
|
Poster
|
Fri 16:30
|
Universal Rates of Empirical Risk Minimization
Steve Hanneke · Mingyue Xu
|
|
