Research Seminar

Winter break.

Past Discussions:

• 8 Dec 2022.

Geoffrey Hinton. The Forward-Forward Algorithm for Training Deep Neural Networks (talk). Discussion leader: Liyan Chen.

• 6 Oct 2022.

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen. Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision. Discussion leader: Liyan Chen.

Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot. Proof-of-Learning: Definitions and Practice. Discussion leader: Benjamin Zhang.

• 15 Sep 2022.

Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, Mark Chen. Hierarchical Text-Conditional Image Generation with CLIP Latents. Discussion leader: Benjamin Zhang.

• 8 Sep 2022.

Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, Omer Reingold, Aaron Roth. Preserving Statistical Validity in Adaptive Data Analysis. Discussion leader: Shiwei Zeng.

In Summer 2022:

• 24 Aug 2022. (3:00pm NY Time)

Alex Kendall, Yarin Gal. What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? Presenter: Liyan Chen.

• 17 Aug 2022.

Fairness in Active Learning. Presenter: Nan Cui.

• 10 Aug 2022.

List-decodable learning with multi-filtering. Presenter: Shiwei Zeng.

• 13 Jul 2022.

Jie Shen, Chicheng Zhang. Attribute-efficient learning of Halfspaces with malicious noise: near-optimal label complexity and noise tolerance. Presenter: Nan Cui.

• 29 Jun 2022.

Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler. Benign overfitting in linear regression. Presenter: Shiwei Zeng.

• 15 Jun 2022.

S. Grace Chang, Bin Yu, Martin Vetterli. Adaptive wavelet thresholding for image denoising and compression. Presenter: Zhuosheng Zhang.

Dan Hendrycks, Norman Mu, Ekin D. Cubuk, Barret Zoph, Justin Gilmer, Balaji Lakshminarayanan. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. Presenter: Wuxinlin Cheng.

• 8 Jun 2022.

Russell Impagliazzo, Rex Lei, Toniann Pitassi, Jessica Sorrell. Reproducibility in Learning. (continued) Presenter: Shiwei Zeng.

Clément Godard, Oisin Mac Aodha, Michael Firman, Gabriel Brostow. Digging Into Self-Supervised Monocular Depth Estimation. Presenter: Liyan Chen.

• 1 Jun 2022.

Russell Impagliazzo, Rex Lei, Toniann Pitassi, Jessica Sorrell. Reproducibility in Learning. Presenter: Shiwei Zeng.

In Spring 2022:

• 30 Mar 2022.

Maria-Florina Balcan, Avrim Blum, Steve Hanneke, Dravyansh Sharma. Robustly-reliable learners under poisoning attacks. Presenter: Shiwei Zeng.

• 23 Mar 2022.

Pranjal Awasthi, Maria Florina Balcan, Philip M. Long. The Power of Localization for Efficiently Learning Linear Separators with Noise. Presenter: Nan Cui.

• 09 Mar 2022.

Nika Haghtalab, Tim Roughgarden, Abhishek Shetty. Smoothed Analysis with Adaptive Adversaries. Presenter: Shiwei Zeng.

• 23 Feb 2022.

Ilai Bistritz, Ariana J. Mann, Nicholas Bambos. Distributed Distillation for On-Device Learning. Presenter: Zhuosheng Zhang.

Yue Xing, Qifan Song, Guang Cheng. On the Algorithmic Stability of Adversarial Training. Presenter: Nan Cui.

• 16 Feb 2022.

Sitan Chen, Adam R. Klivans, Raghu Meka. Learning Deep ReLU Networks Is Fixed-Parameter Tractable. Presenter: Shiwei Zeng.

Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Rémi Tachet des Combes. A single gradient step finds adversarial examples on random two-layers neural networks. Presenter: Nan Cui.

Before 2021:

• 3 Dec 2021.

Ilias Diakonikolas, Sushrut Karmalkar, Daniel Kane, Eric Price, Alistair Stewart. Outlier-robust high-dimensional sparse estimation via iterative filtering. Presenter: Shiwei Zeng.

Metric-fair active learning. Presenter: Nan Cui.

• 19 Nov 2021.

Efficient active learning. Presenter: Nan Cui.

• 12 Nov 2021.

Omar Montasser, Steve Hanneke, Nathan Srebro. Adversarially robust learning with unknown perturbation sets (continued). Presenter: Nan Cui.

• 5 Nov 2021.

Justin Khim, Po-Ling Loh. Adversarial risk bound via function transformation (continued). Presenter: Nan Cui.

Omar Montasser, Steve Hanneke, Nathan Srebro. Adversarially robust learning with unknown perturbation sets. Presenter: Shiwei Zeng.

• 29 Oct 2021.

Justin Khim, Po-Ling Loh. Adversarial risk bound via function transformation (continued). Presenter: Nan Cui.

• 22 Oct 2021.

Adversarially robust learning of threshold functions with a large margin. Presenter: Shiwei Zeng.

Justin Khim, Po-Ling Loh. Adversarial risk bound via function transformation. Presenter: Nan Cui.

• 14 Jun, 2021.

A statistical perspective of distillation. Presenter: Tianhao Zhu.

To be scheduled:

Huan Xu, Shie Mannor. Robustness and Generalization. Presenter: .

Sitan Chen, Sinho Chewi, Jerry Li, Yuanzhi Li, Adil Salim, Anru R. Zhang. Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions. Discussion leader: Shiwei Zeng.