NeurIPS 2024 Workshop SciForDL Submissions

How Learning Rates Shape Neural Network Focus: Insights from Example Ranking
Ekaterina Lobacheva, Keller Jordan, Aristide Baratin, Nicolas Le Roux
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Twin Studies of Factors in OOD Generalization
Victoria R Li, Jenny Kaufmann, David Alvarez-Melis, Naomi Saphra
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- SciForDL Poster
- Readers: Everyone
Causation Does Not Imply Correlation: A Study of Circuit Mechanisms and Model Behaviors
Jenny Kaufmann, Victoria R Li, Martin Wattenberg, David Alvarez-Melis, Naomi Saphra
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Robust Learning in Bayesian Parallel Branching Graph Neural Networks: The Narrow Width Limit
Zechen Zhang, Haim Sompolinsky
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
The Pitfalls of Memorization: When Memorization Hinders Generalization
Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
SolidMark: How to Evaluate Memorization in Image Generative Models
Nicky Kriplani, Minh Pham, Malikka Rajshahi, Chinmay Hegde, Niv Cohen
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Structured Identity Mapping Learning As a Model for Compositional Generalization in Generative Models
Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana, Maya Okawa, Wei Hu, Hidenori Tanaka
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Improving Deep Learning Speed and Performance through Synaptic Neural Balance
Antonios Alexos, Ian Domingo, Pierre Baldi
- Published: 10 Oct 2024, Last Modified: 16 Apr 2025
- SciForDL Poster
- Readers: Everyone
Memorization to Generalization: The Emergence of Diffusion Models from Associative Memory
Bao Pham, Gabriel Raya, Matteo Negri, Mohammed J Zaki, Luca Ambrogioni, Dmitry Krotov
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Oral
- Readers: Everyone
Evaluating Loss Landscapes from a Topology Perspective
Tiankai Xie, Caleb Geniesse, Jiaqing Chen, Yaoqing Yang, Dmitriy Morozov, Michael W. Mahoney, Ross Maciejewski, Gunther H. Weber
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs
Daniel J Lee, Stefan Heimersheim
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Emergence of Hierarchical Emotion Representations in Large Language Models
Bo Zhao, Maya Okawa, Eric J Bigelow, Rose Yu, Tomer Ullman, Hidenori Tanaka
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Learning Stochastic Rainbow Networks
Vivian White, Muawiz Sajjad Chaudhary, Guy Wolf, Guillaume Lajoie, Kameron Decker Harris
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Emergent properties with repeated examples
Francois Charton, Julia Kempe
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
Anton Xue, Avishree Khare, Rajeev Alur, Surbhi Goel, Eric Wong
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Training Dynamics of Convolutional Neural Networks for Learning the Derivative Operator
Erik Y. Wang, Yongji Wang, Ching-Yao Lai
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Hiding in a Plain Sight: Out-of-Distribution Data in the Logit Space Embeddings
Vangjush Kostandin Komini, Sarunas Girdzijauskas
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Impact of Label Noise on Learning Complex Features
Rahul Vashisht, P Krishna Kumar, Harsha Vardhan Govind, Harish Guruprasad Ramaswamy
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Token-token correlations predict the scaling of the test loss with the number of input tokens
Francesco Cagnetta, Matthieu Wyart
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
How rare events shape the learning curves of hierarchical data
Hyunmo Kang, Francesco Cagnetta, Matthieu Wyart
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Is Expressivity Essential for the Predictive Performance of Graph Neural Networks?
Fabian Jogl, Pascal Welke, Thomas Gärtner
- Published: 10 Oct 2024, Last Modified: 08 Dec 2024
- SciForDL Poster
- Readers: Everyone
A Continuous-Time Analysis of Adaptive Optimization and Normalization
Rhys Gould, Hidenori Tanaka
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Understanding the Limitations of B-Spline KANs: Convergence Dynamics and Computational Efficiency
Avik Pal, Dipankar Das
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Is Saliency Really Captured By Gradient?
Nehal Yasin, Jonathon Hare, Antonia Marcu
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Testing knowledge distillation theories with dataset size
Giulia Lanzillotta, Felix Sarnthein, Gil Kur, Thomas Hofmann, Bobby He
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone