NeurIPS 2024 Workshop M3L Submissions

Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization
Matan Schliserman, Tomer Koren
- Published: 11 Oct 2024, Last Modified: 05 Dec 2024
- M3L Poster
- Readers: Everyone
Exploring Task Affinities through NTK Alignment and Early Training Dynamics in Multi-Task Learning
Yoann Morello, Emilie Gregoire, Sam Verboven
- Published: 11 Oct 2024, Last Modified: 01 Dec 2024
- M3L Poster
- Readers: Everyone
Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural Networks
Ouns El Harzli, Bernardo Cuenca Grau
- Published: 11 Oct 2024, Last Modified: 02 Dec 2024
- M3L Poster
- Readers: Everyone
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
Jonas Hübotter, Sascha Bongni, Ido Hakimi, Andreas Krause
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Adversarial Attacks as Near-Zero Eigenvalues in the Empirical Kernel of Neural Networks
Ouns El Harzli, Bernardo Cuenca Grau
- Published: 11 Oct 2024, Last Modified: 02 Dec 2024
- M3L Poster
- Readers: Everyone
Can Bayesian Neural Networks Make Confident Predictions?
Katharine Fisher
- Published: 11 Oct 2024, Last Modified: 09 Dec 2024
- M3L Poster
- Readers: Everyone
Algorithmic Stability of Minimum-Norm Interpolating Deep Neural Networks
Ouns El Harzli, Yoonsoo Nam, Ilja Kuzborskij, Bernardo Cuenca Grau, Ard A. Louis
- Published: 11 Oct 2024, Last Modified: 01 Dec 2024
- M3L Poster
- Readers: Everyone
Simple and Effective Masked Diffusion Language Models
Subham Sekhar Sahoo, Marianne Arriola, Aaron Gokaslan, Yair Schiff, Edgar Mariano Marroquin, Justin T Chiu, Alexander M Rush, Volodymyr Kuleshov
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks
Emily Liu
- Published: 11 Oct 2024, Last Modified: 01 Dec 2024
- M3L Poster
- Readers: Everyone
Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
Francesco Mori, Stefano Sarao Mannelli, Francesca Mignacco
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Label Noise: Ignorance Is Bliss
Yilun Zhu, Jianxin Zhang, Aditya Gangrade, Clayton Scott
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection
Aaron Alvarado Kristanto Julistiono, Davoud Ataee Tarzanagh, Navid Azizan
- Published: 11 Oct 2024, Last Modified: 09 Dec 2024
- M3L Poster
- Readers: Everyone
On the Implicit Relation between Low-Rank Adaptation and Differential Privacy
Saber Malekmohammadi, Golnoosh Farnadi
- Published: 11 Oct 2024, Last Modified: 30 Nov 2024
- M3L Poster
- Readers: Everyone
Improving the Gaussian Approximation in Neural Networks: Para-Gaussians and Edgeworth Expansions
Mihai Nica, Janosch Ortmann
- Published: 11 Oct 2024, Last Modified: 29 Nov 2024
- M3L Poster
- Readers: Everyone
Diffusion Models With Learned Adaptive Noise Processes
Subham Sekhar Sahoo, Aaron Gokaslan, Christopher De Sa, Volodymyr Kuleshov
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
Yibo Jiang, Goutham Rajendran, Pradeep Kumar Ravikumar, Bryon Aragam
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
Liu Ziyin, Mingze Wang, Hongchao Li, Lei Wu
- Published: 11 Oct 2024, Last Modified: 04 Dec 2024
- M3L Poster
- Readers: Everyone
Information-Theoretic Foundations for Neural Scaling Laws
Hong Jun Jeon, Benjamin Van Roy
- Published: 11 Oct 2024, Last Modified: 01 Dec 2024
- M3L Poster
- Readers: Everyone
Diffusion Model Learns Low-Dimensional Distributions via Subspace Clustering
Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Information-Theoretic Generalization Bounds for Batch Reinforcement Learning
Xingtu Liu
- Published: 11 Oct 2024, Last Modified: 12 Nov 2024
- M3L Poster
- Readers: Everyone
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
Anchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Sample compression unleashed : New generalization bounds for real valued losses
Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
The Crucial Role of Samplers in Online Direct Preference Optimization
Ruizhe Shi, Runlong Zhou, Simon Shaolei Du
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks
Yongyi Yang, Jiaming Yang, Wei Hu, Michal Derezinski
- Published: 11 Oct 2024, Last Modified: 10 Nov 2024
- M3L Poster
- Readers: Everyone
Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
Mitsuhiro Fujikawa, Youhei Akimoto, Jun Sakuma, Kazuto Fukuchi
- Published: 11 Oct 2024, Last Modified: 26 Nov 2024
- M3L Poster
- Readers: Everyone