Dimitris Tsipras


I am a postdoctoral researcher in Computer Science at Stanford University, mentored by Percy Liang and Greg Valiant. My research is focused on understanding and improving modern machine learning methods, with a focus on reliability. My work is supported by Open Philanthropy.

I got my PhD in Computer Science from MIT where I was advised by Aleksander Mądry. Before that, I did my undergrad in ECE at NTUA, Greece, where my thesis was advised by Dimitris Fotakis.

my face tsipras@stanford.edu

Selected papers Show all Show selected
(* denotes equal contribution)


What Can Transformers Learn In-Context? A Case Study of Simple Function Classes
Shivam Garg*, Dimitris Tsipras*, Percy Liang, Gregory Valiant
NeurIPS 2022 (oral presentation)
Code

Editing a classifier by rewriting its prediction rules
Shibani Santurkar*, Dimitris Tsipras*, Mahi Elango, David Bau, Antonio Torralba, Aleksander Mądry
NeurIPS 2021
Blog post, Code

Combining Diverse Feature Priors
Saachi Jain*, Dimitris Tsipras*, Aleksander Mądry
ICML 2022
Blog post, Code

Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
TPAMI 2022

BREEDS: Benchmarks for Subpopulation Shift
Shibani Santurkar*, Dimitris Tsipras*, Aleksander Mądry
ICLR 2021
Blog post, Benchmarks

From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Dimitris Tsipras*, Shibani Santurkar*, Logan Engstrom, Andrew Ilyas, Aleksander Mądry
ICML 2020
Blog post, ImageNet annotations

Identifying Statistical Bias in Dataset Replication
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Mądry
ICML 2020
Blog post, Code

Image Synthesis with a Single (Robust) Classifier
Shibani Santurkar*, Dimitris Tsipras*, Brandon Tran*, Andrew Ilyas*, Logan Engstrom*, Aleksander Mądry
NeurIPS 2019
Blog post, Code/Notebooks, Demo

Learning Perceptually-Aligned Representations via Adversarial Robustness
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar*, Dimitris Tsipras*, Brandon Tran*, Aleksander Mądry
Blog post, Code/Notebooks

Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas*, Shibani Santurkar*, Dimitris Tsipras*, Logan Engstrom*, Brandon Tran, Aleksander Mądry
NeurIPS 2019 (spotlight presentation)
Blog post, Datasets

On Evaluating Adversarial Robustness
Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, Aleksander Mądry, Alexey Kurakin

Label-Consistent Backdoor Attacks
Alexander Turner, Dimitris Tsipras, Aleksander Mądry

A Closer Look at Deep Policy Gradients
Andrew Ilyas*, Logan Engstrom*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Mądry
ICLR 2020 (oral presentation)
Blog post: part 1, part 2, part 3

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Mądry
ICLR 2020 (oral presentation)
Code

Robustness May Be at Odds with Accuracy
Dimitris Tsipras*, Shibani Santurkar*, Logan Engstrom*, Alexander Turner, Aleksander Mądry
ICLR 2019

How Does Batch Normalization Help Optimization?
Shibani Santurkar*, Dimitris Tsipras*, Andrew Ilyas*, Aleksander Mądry
NeurIPS 2018 (oral presentation)
Blog post, 3-minute video

Adversarially Robust Generalization Requires More Data
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Mądry
NeurIPS 2018 (spotlight presentation)

Exploring the Landscape of Spatial Robustness
Logan Engstrom*, Brandon Tran*, Dimitris Tsipras*, Ludwig Schmidt, Aleksander Mądry
ICML 2019
Code

Towards Deep Learning Models Resistant to Adversarial Attacks
(α-β order) Aleksander Mądry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu
ICLR 2018
Blog post: part 1 and part 2, MNIST Challenge, CIFAR10 Challenge

Matrix Scaling and Balancing via Box Constrained Newton's Method and Interior Point Methods
(α-β order) Michael B. Cohen, Aleksander Mądry, Dimitris Tsipras, Adrian Vladu
FOCS 2017

Efficient Money Burning in General Domains
(α-β order) Dimitris Fotakis, Dimitris Tsipras, Christos Tzamos, Manolis Zampetakis
SAGT 2015
Invited to special issue of Theory of Computing Systems