Skip to yearly menu bar Skip to main content


(6 events)   Time zone: Conference local time zone  
Show all
Toggle Poster Visibility
Oral
Fri Apr 24 10:30 AM -- 10:40 AM (-03) @ 204 A/B None
The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm
In Oral Session 3E Learning dynamics and optimization II
Noah Amsel ⋅ David Persson ⋅ Christopher Musco ⋅ Robert M. Gower
[ OpenReview] 
Oral
Fri Apr 24 10:42 AM -- 10:52 AM (-03) @ 204 A/B None
Temporal superposition and feature geometry of RNNs under memory demands
In Oral Session 3E Learning dynamics and optimization II
Pratyaksh Sharma ⋅ Alexandra M Proca ⋅ Lucas Prieto ⋅ Pedro Mediano
[ OpenReview] 
Oral
Fri Apr 24 10:54 AM -- 11:04 AM (-03) @ 204 A/B None
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
In Oral Session 3E Learning dynamics and optimization II
Leonardo Defilippis ⋅ Yizhou Xu ⋅ Julius Girardin ⋅ Vittorio Erba ⋅ Emanuele Troiani ⋅ Lenka Zdeborova ⋅ Bruno Loureiro ⋅ Florent Krzakala
[ OpenReview] 
Oral
Fri Apr 24 11:06 AM -- 11:16 AM (-03) @ 204 A/B None
Efficient Resource-Constrained Training of Transformers via Subspace Optimization
In Oral Session 3E Learning dynamics and optimization II
Le-Trung Nguyen ⋅ Enzo Tartaglione ⋅ Van-Tam Nguyen
[ OpenReview] 
Oral
Fri Apr 24 11:18 AM -- 11:28 AM (-03) @ 204 A/B None
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
In Oral Session 3E Learning dynamics and optimization II
Haiquan Qiu ⋅ Quanming Yao
[ OpenReview] 
Oral
Fri Apr 24 11:30 AM -- 11:40 AM (-03) @ 204 A/B None
HATSolver: Learning Gröbner Bases with Hierarchical Attention Transformers
In Oral Session 3E Learning dynamics and optimization II
Mohamed Malhou ⋅ Ludovic Perret ⋅ Kristin Lauter
[ OpenReview]