Aleksander Mądry I am a Professor of Computer Science in the MIT EECS Department, a member of CSAIL and of the Theory of Computation group. I received my Ph.D. from MIT in 2011. Prior to joining the MIT's faculty, I spent a year as a postdoctoral researcher at Microsoft Research New England and then I was on the faculty of EPFL until early 2015. I am the Director of the MIT Center for Deployable Machine Learning and the Faculty Lead of the CSAIL-MSR Trustworthy and Robust AI Collaboration. Research Interests: My research spans algorithmic graph theory, optimization and machine learning. In particular, I have a strong interest in building on the existing machine learning techniques to forge a decision-making toolkit that is reliable and well-understood enough to be safely and responsibly deployed in the real world. To learn more about my work in machine learning, see here or take a look at our blog. Email: madry@mit.edu    CV    Twitter    Contact info Mailing address: Aleksander Mądry Office 32-G806 32 Vassar Street Cambridge, MA 02139   Phone:   (Note: Email is by far  the best way to reach me.) Interested in working with me? Apply to our PhD program! (Please do not email me regarding this matter - just mention my name in your application.) Also, please do not contact me regarding internship positions (unless you are an MIT student).

Selected Papers (Show all):

• Do Adversarially Robust ImageNet Models Transfer Better?, Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Mądry.
  NeurIPS 2020. Oral presentation.
• On Adaptive Attacks to Adversarial Example Defenses, Florian Tramer, Nicholas Carlini, Wieland Brendel, Aleksander Mądry.
  NeurIPS 2020.
• Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs, Kyriakos Axiotis, Aleksander Mądry, Adrian Vladu.
  FOCS 2020.
• From ImageNet to Image Classification: Contextualizing Progress on Benchmarks, Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Andrew Ilyas, Aleksander Mądry.
  ICML 2020.
• Identifying Statistical Bias in Dataset Replication, Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Mądry.
  ICML 2020.
Implementation Matters in Deep RL: 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.
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.
• Adversarial Examples Are Not Bugs, They Are Features, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Mądry.
  NeurIPS 2019. Spotlight presentation.
Image Synthesis with a Single (Robust) Classifier, Shibani Santurkar, Dimitris Tsipras, Brandon Tran, Andrew Ilyas, Logan Engstrom, Aleksander Mądry.
NeurIPS 2019.
Exploring the Landscape of Spatial Robustness, Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, Aleksander Mądry.
ICML 2019.
• Robustness May Be at Odds with Accuracy, Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, Aleksander Mądry.
  ICLR 2019.
Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors, Andrew Ilyas, Logan Engstrom, Aleksander Mądry.
ICLR 2019.
Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability, Kai Xiao, Vincent Tjeng, Nur Muhammad Shafiullah, Aleksander Mądry.
ICLR 2019.
• How Does Batch Normalization Help Optimization?, Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Mądry.
  NeurIPS 2018. Oral presentation.
Adversarially Robust Generalization Requires More Data, Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Mądry.
NeurIPS 2018. Spotlight presentation.
Spectral Signatures in Backdoor Attacks, Brandon Tran, Jerry Li, Aleksander Mądry.
NeurIPS 2018.
A Classification-Based Study of Covariate Shift in GAN Distributions, Shibani Santurkar, Ludwig Schmidt, Aleksander Mądry.
ICML 2018.
On the Limitations of First-Order Approximation in GAN Dynamics, with Jerry Li, John Peebles, Ludwig Schmidt.
ICML 2018.
• Towards Deep Learning Models Resistant to Adversarial Attacks, with Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu.
  ICLR 2018.
• k-Server via Multiscale Entropic Regularization, Sebastien Bubeck, Michael B. Cohen, James R. Lee, Yin Tat Lee, Aleksander Mądry.
  STOC 2018. Invited to the special issue.
Round Compression for Parallel Matching Algorithms, Artur Czumaj, Jakub Łącki, Aleksander Mądry, Slobodan Mitrović, Krzysztof Onak, Piotr Sankowski.
STOC 2018. Invited to the special issue.
A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians, Aleksander Mądry, Slobodan Mitrović, Ludwig Schmidt.
AISTATS 2018.
Matrix Scaling and Balancing via Box Constrained Newton’s Method and Interior Point Methods, Michael B. Cohen, Aleksander Mądry, Dimitris Tsipras, Adrian Vladu.
FOCS 2017.
Negative-Weight Shortest Paths and Unit Capacity Minimum Cost Flow in O(m^10/7 log W) Time, Michael B. Cohen, Aleksander Mądry, Piotr Sankowski, Adrian Vladu.
SODA 2017.
• Computing Maximum Flow with Augmenting Electrical Flows, Aleksander Mądry.
  FOCS 2016. Invited to the special issue.
On the Resiliency of Randomized Routing Against Multiple Edge Failures, Marco Chiesa, Andrei Gurtov, Aleksander Mądry, Slobodan Mitrović, Ilya Nikolaevskiy, Michael Schapira, Scott Shenker.
ICALP 2016.
The Quest for Resilient (Static) Forwarding Tables, with Marco Chiesa, Ilya Nikolaevskiy, Slobodan Mitrović, Aurojit Panda, Andrei Gurtov, Michael Schapira, Scott Shenker.
INFOCOM 2016.
Fast Generation of Random Spanning Trees and the Effective Resistance Metric, Aleksander Mądry, Damian Straszak, Jakub Tarnawski.
SODA 2015.
On the Configuration LP for Maximum Budgeted Allocation, Christos Kalaitzis, Aleksander Mądry, Alantha Newman, Lukáš Poláček, Ola Svensson.
IPCO 2014. Mathematical Programming, Volume 154 Issue 1, 2015.
• Navigating Central Path with Electrical Flows: from Flows to Matchings, and Back, Aleksander Mądry.
  FOCS 2013. Best Paper Award. Invited to the Journal of the ACM.
Runtime Guarantees for Regression Problems, Hui Han Chin, Aleksander Mądry, Gary L. Miller, Richard Peng.
ITCS 2013.
The Semi-stochastic Ski-rental Problem, Aleksander Mądry, Debmalya Panigrahi.
FSTTCS 2011.
• A Polylogarithmic-Competitive Algorithm for the k-Server Problem, Nikhil Bansal, Niv Buchbinder, Aleksander Mądry, Seffi Naor.
  FOCS 2011. Best Paper Award. Journal of the ACM, Volume 62 Issue 5, 2015 (invited paper).
• From Graphs to Matrices, and Back: New Techniques for Graph Algorithms
  My Ph.D. thesis, MIT, EECS Department, 2011. ACM Doctoral Dissertation Award Honorable Mention. George M. Sprowls Award (for best MIT doctoral theses in CS).
• Electrical Flows, Laplacian Systems, and Faster Approximation of Maximum Flow in Undirected Graphs , Paul Christiano, Jonathan Kelner, Aleksander Mądry, Daniel Spielman, Shang-Hua Teng.
  STOC 2011. Best Paper Award. Invited to the Journal of the ACM.
Fast Approximation Algorithms for Cut-based Problems in Undirected Graphs, Aleksander Mądry.
FOCS 2010.
Faster Approximation Schemes for Fractional Multicommodity Flow Problems via Dynamic Graph Algorithms, Aleksander Mądry.
STOC 2010.
• An O(log n/log log n)-approximation Algorithm for the Asymmetric Traveling Salesman Problem, Arash Asadpour, Michel Goemans, Aleksander Mądry, Shayan Oveis Gharan, Amin Saberi,
  SODA 2010. Best Paper Award.
Faster Generation of Random Spanning Trees, Jonathan Kelner, Aleksander Mądry.
FOCS 2009.
Maximum Bipartite Flow in Networks with Adaptive Channel Width, Yossi Azar, Aleksander Mądry, Thomas Moscibroda, Debmalya Panigrahi, Aravind Srinivasan.
ICALP 2009. Theoretical Computer Science, vol. 412(24), 2011. Special Issue.
Susceptible Two-Party Quantum Computations, Andreas Jacoby, Maciej Liśkiewicz, Aleksander Mądry.
ICITS 2008.
Geometric Aspects of Online Packet Buffering: An Optimal Randomized Algorithm for Two Buffers, Marcin Bienkowski, Aleksander Mądry.
LATIN 2008.
Data Exchange: On the Complexity of Answering Queries with Inequalities , Aleksander Mądry.
Information Processing Letters, Vol. 94, Issue 6 (June 2005), p. 253 - 257.

Teaching:

• 6.046: Design and Analysis of Algorithms, Fall 2020.
• 6.046: Design and Analysis of Algorithms, Spring 2020.
• 6.S979: Topics in Deployable ML, Fall 2019.
• 6.854: Advanced Algorithms, Fall 2019.
• 6.046: Design and Analysis of Algorithms, Spring 2019.
• 6.854: Advanced Algorithms, Fall 2018.
• 6.883: Science of Deep Learning, Spring 2018.
• 6.046: Design and Analysis of Algorithms, Spring 2018.
• 6.046: Design and Analysis of Algorithms, Spring 2017.
• 6.854: Advanced Algorithms, Fall 2016.
• 6.006: Introduction to Algorithms, Spring 2016.
• 6.S978: Graphs, Linear Algebra, and Optimization, Fall 2015.
• Theoretical Computer Science, Fall 2014.
• Theory of Computation, Spring 2014.
• Theoretical Computer Science, Fall 2013.
• Advanced Theoretical Computer Science, Spring 2013.
• Theory Gems, Fall 2012.