LIONS @ NeurIPS 2023

NeurIPS logo © 2023/

NeurIPS logo © 2023/

8 papers from the LIONS group have been accepted to the 2023 edition of NeurIPS conference. Congratulations to all!
This year NeurIPS conference and workshops will be held again in New Orleans, USA from 10th to 16th December.

Below is a list of accepted papers:

  1. Exponential Lower Bounds for Fictitious Play in Potential Games by Ioannis Panageas, Nikolaos Patris, Stratis Skoulakis, Volkan Cevher
  2. Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling by Zhenyu Zhu, Francesco Locatello, Volkan Cevher
  3. Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks by Jiayuan Ye, Zhenyu Zhu, Fanghui Liu, Reza Shokri, Volkan Cevher
  4. Maximum independent set: Self-training through dynamic programming by Lorenzo Brusca, Lars C.P.M. Quaedvlieg, Stratis Skoulakis, Grigorios Chrysos, Volkan Cevher
  5. Efficient Online Clustering with Moving Costs by Dimitris Christou, Stratis Skoulakis, Volkan Cevher (spotlight)
  6. Stable Nonconvex-Nonconcave Training via Linear Interpolation by Thomas Pethick, Wanyun Xie, Volkan Cevher (spotlight)
  7. On the Convergence of Shallow Transformers by Yongtao Wu, Fanghui Liu, Grigorios Chrysos, Volkan Cevher
  8. Alternation makes the adversary weaker in two-player games by Volkan Cevher, Ashok Cutkosky, Ali Kavis, Georgios Piliouras, Stratis Skoulakis, Luca Viano (spotlight)