Ludwig Schmidt

I am a postdoc in computer science at UC Berkeley. My advisors are Moritz Hardt, Ben Recht, and Martin Wainwright. I am broadly interested in the foundations of machine learning, with a focus on making the practice of machine learning more reliable. E-mail: ludwig@berkeley.edu

Before coming to Berkeley, I received my PhD from MIT, where I was fortunate to be advised by Piotr Indyk. During my PhD I also spent some time at Google Brain working with Yoram Singer and Kunal Talwar.

Selected publications

• Do ImageNet Classifiers Generalize to ImageNet?
  Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, Vaishaal Shankar
  Preprint, 2019

• Towards Deep Learning Models Resistant to Adversarial Attacks
  Aleksander Mądry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu
  ICLR 2018 (International Conference on Learning Representations)

• Algorithms Above the Noise Floor
  Ludwig Schmidt
  PhD thesis, 2018
  George M. Sprowls Award (for best PhD theses in computer science at MIT)

• A Nearly-Linear Time Framework for Graph-Structured Sparsity
  Chinmay Hegde, Piotr Indyk, Ludwig Schmidt
  ICML 2015 (International Conference on Machine Learning)
  Best paper award

• Practical and Optimal LSH for Angular Distance
  Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya Razenshteyn, Ludwig Schmidt
  NIPS 2015 (Conference on Neural Information Processing Systems)