NeurIPS 2023 Workshop OPT Submissions

Generalisable Agents for Neural Network Optimisation
Kale-ab Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan John de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Testing Approximate Stationarity Concepts for Piecewise Affine Functions and Extensions
Lai Tian, Anthony Man-Cho So
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
On the Convergence of Local SGD Under Third-Order Smoothness and Hessian Similarity
Ali Zindari, Ruichen Luo, Sebastian U Stich
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Escaping mediocrity: how two-layer networks learn hard generalized linear models
Luca Arnaboldi, Florent Krzakala, Bruno Loureiro, Ludovic Stephan
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Oral
- Readers: Everyone
Optimal Transport for Kernel Gaussian Mixture Models
Jung Hun Oh, Rena Elkin, Anish Kumar Simhal, Jiening Zhu, Joseph O Deasy, Allen Tannenbaum
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Cup Curriculum: Curriculum Learning on Model Capacity
Luca Scharr, Vanessa Toborek
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
(Un)certainty selection methods for Active Learning on Label Distributions
James Spann, Pratik Sanjay Bongale, Christopher M Homan
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Global CFR: Meta-Learning in Self-Play Regret Minimization
David Sychrovský, Michal Sustr, Michael Bowling, Martin Schmid
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Fair Representation in Submodular Subset Selection: A Pareto Optimization Approach
Adriano Fazzone, Yanhao Wang, Francesco Bonchi
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
How to Guess a Gradient
Utkarsh Singhal, Brian Cheung, Kartik Chandra, Jonathan Ragan-Kelley, Joshua B. Tenenbaum, Tomaso A Poggio, Stella X. Yu
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks
Mrinal Mathur, Sergey M. Plis
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Why Adam Outperforms Gradient Descent on Language Models: A Heavy-Tailed Class Imbalance Problem
Robin Yadav, Frederik Kunstner, Mark Schmidt, Alberto Bietti
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
SGD batch saturation for training wide neural networks
Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yian Ma
- Published: 26 Oct 2023, Last Modified: 15 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
MSL: An Adaptive Momentem-based Stochastic Line-search Framework
Chen Fan, Sharan Vaswani, Christos Thrampoulidis, Mark Schmidt
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Adagrad Promotes Diffuse Solutions In Overparameterized Regimes
Andrew Rambidis, Jiayi Wang
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Unnormalized Density Estimation with Root Sobolev Norm Regularization
Mark Kozdoba, Binyamin Perets, Shie Mannor
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Level Set Teleportation: the Good, the Bad, and the Ugly
Aaron Mishkin, Alberto Bietti, Robert M. Gower
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets
Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
FaDE: Fast DARTS Estimator on Hierarchical NAS Spaces
Simon Neumeyer, Julian Stier, Michael Granitzer
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Fair Minimum Representation Clustering
Connor Lawless, Oktay Gunluk
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
On the Parallel Complexity of Multilevel Monte Carlo in Stochastic Gradient Descent
Kei Ishikawa
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Stochastic Optimization under Hidden Convexity
Ilyas Fatkhullin, Niao He, Yifan Hu
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs
Zihan Zhou, Honghao Wei, Lei Ying
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
Nuoya Xiong, Lijun Ding, Simon Shaolei Du
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Average-Constrained Policy Optimization
Akhil Agnihotri, Rahul Jain, Haipeng Luo
- Published: 26 Oct 2023, Last Modified: 13 Dec 2023
- NeurIPS 2023 Workshop Poster
- Readers: Everyone