ICML 2024 Workshop HiLD Submissions

Looking at Deep Learning Phenomena Through a Telescoping Lens
Alan Jeffares, Alicia Curth, Mihaela van der Schaar
- Published: 16 Jun 2024, Last Modified: 19 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Emergent representations in networks trained with the Forward-Forward algorithm
Niccolo Tosato, Lorenzo Basile, Emanuele Ballarin, Giuseppe De Alteriis, Alberto Cazzaniga, Alessio ansuini
- Published: 16 Jun 2024, Last Modified: 12 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Neural collapse versus low-rank bias: Is deep neural collapse really optimal?
Peter Súkeník, Marco Mondelli, Christoph H. Lampert
- Published: 16 Jun 2024, Last Modified: 16 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Gradient Descent with Polyak’s Momentum Finds Flatter Minima via Large Catapults
Prin Phunyaphibarn, Junghyun Lee, Bohan Wang, Huishuai Zhang, Chulhee Yun
- Published: 16 Jun 2024, Last Modified: 17 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Provable Tempered Overfitting of Minimal Nets and Typical Nets
Itamar Harel, William M. Hoza, Gal Vardi, Itay Evron, Nathan Srebro, Daniel Soudry
- Published: 16 Jun 2024, Last Modified: 20 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution
Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi
- Published: 16 Jun 2024, Last Modified: 18 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Decomposing and Editing Predictions by Modeling Model Computation
Harshay Shah, Andrew Ilyas, Aleksander Madry
- Published: 16 Jun 2024, Last Modified: 16 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
An exactly solvable model for emergence and scaling laws
Yoonsoo Nam, Nayara Fonseca, Seok Hyeong Lee, Chris Mingard, Ard A. Louis
- Published: 16 Jun 2024, Last Modified: 10 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
On the metastability of learning algorithms in physics-informed neural networks: a case study on Schr\"{o}dinger operators
Alessandro Maria Selvitella
- Published: 16 Jun 2024, Last Modified: 17 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
Moritz Haas, Jin Xu, Volkan Cevher, Leena Chennuru Vankadara
- Published: 16 Jun 2024, Last Modified: 19 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Probability Tools for Sequential Random Projection
Yingru Li
- Published: 16 Jun 2024, Last Modified: 19 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Simple, unified analysis of Johnson-Lindenstrauss with applications
Yingru Li
- Published: 16 Jun 2024, Last Modified: 19 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Does SGD really happen in tiny subspaces?
Minhak Song, Kwangjun Ahn, Chulhee Yun
- Published: 16 Jun 2024, Last Modified: 18 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
When Are Bias-Free ReLU Networks Like Linear Networks?
Yedi Zhang, Andrew M Saxe, Peter E. Latham
- Published: 16 Jun 2024, Last Modified: 08 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Early Period of Training Impacts Out-of-Distribution Generalization
Chen Cecilia Liu, Iryna Gurevych
- Published: 16 Jun 2024, Last Modified: 03 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
A Random Matrix Analysis of Learning with Noisy Labels
Aymane El Firdoussi, Mohamed El Amine Seddik
- Published: 16 Jun 2024, Last Modified: 28 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Understanding Nonlinear Implicit Bias via Region Counts in Input Space
Jingwei Li, Jing Xu, Zifan Wang, Huishuai Zhang, Jingzhao Zhang
- Published: 16 Jun 2024, Last Modified: 05 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
Hugo Cui, Freya Behrens, Florent Krzakala, Lenka Zdeborova
- Published: 16 Jun 2024, Last Modified: 10 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Gradient descent induces alignment between weights and the pre-activation tangents for deep non-linear networks
Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala
- Published: 16 Jun 2024, Last Modified: 19 Jul 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Progress Measures for Grokking on Real-world Tasks
Satvik Golechha
- Published: 16 Jun 2024, Last Modified: 20 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Three Mechanisms of Feature Learning in an Analytically Solvable Model
Yizhou Xu, Liu Ziyin
- Published: 16 Jun 2024, Last Modified: 18 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
Asymptotic Dynamics for Delayed Feature Learning in a Toy Model
Blake Bordelon, Tanishq Kumar, Samuel J. Gershman, Cengiz Pehlevan
- Published: 16 Jun 2024, Last Modified: 16 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone
ReLU Characteristic Activation Analysis
Wenlin Chen, Hong Ge
- Published: 16 Jun 2024, Last Modified: 17 Jun 2024
- HiLD at ICML 2024 Poster
- Readers: Everyone