Shibani Santurkar, We study the roots of algorithmic progres
- Shibani Santurkar, We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Policy Optimization Machine Learning Beyond Accuracy: A Features Perspective on Model Generalization Shibani Santurkar, Aleksander Madry, Nir Shavit January 2021 research-article The focus of my research is on building a machine learning (ML) toolkit that allows for the reliable, robust, and auditable deployment of models in the real world. Facebook gives people the power to share and makes the world more open and connected. I got my PhD from MIT, where I was fortunate to be advised by Aleksander Madry and Shibani Santurkar OpenAI Verified email at stanford. The View a PDF of the paper titled How Does Batch Normalization Help Optimization?, by Shibani Santurkar and 3 other authors View a PDF of the paper titled BREEDS: Benchmarks for Subpopulation Shift, by Shibani Santurkar and 2 other authors How Does Batch Normalization Help Optimization? Shibani Santurkar MIT shibani@mit. The author has contributed to research in topics: Computer science & Robustness (computer science). edu - Homepage Machine Learning I'm a Machine Learning researcher at MIT. Join Facebook to connect with Shibani Santurkar and others you may know. I was a postdoc in Computer Science at Stanford, working with Tatsu Hashimoto, Percy Liang, and Tengyu Ma. Artificial Neural Network,Bit Error,Bit Error Rate,Bitrate,Bound State,Coding Tree,Compression Algorithm,Compression Factor,Compression Level,Concentration Profiles The Simons Institute for the Theory of Computing is the world's leading venue for collaborative research in theoretical computer science. Read Shibani Santurkar's latest research, browse their coauthor's research, and play around with their algorithms Whose Opinions Do Language Models Reflect? Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori Hashimoto Published: 24 Apr 2023, Last Modified: 15 Jun 2023 ICML International Conference on Learning Representations (ICLR)（2023） Cited 19 Views 121 Bibtex Whose Opinions Do Language Models Reflect Shibani Santurkar, Esin Durmus, Faisal Ladhak, Shibani SANTURKAR | Cited by 15 | of Indian Institute of Technology Bombay, Mumbai (IIT Bombay) | Read 3 publications | Contact Shibani SANTURKAR Joint work with Logan Engstrom, Andrew Ilyas, Aleksander Madry and Dimitris Tsipras. Digital circuit design for a high View a PDF of the paper titled Whose Opinions Do Language Models Reflect?, by Shibani Santurkar and 5 other authors 301 Followers, 386 Following, 7 Posts - Shibani Santurkar (@shibanisanturkar) on Instagram: "" Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Andrew Ilyas, Aleksander Madry: From ImageNet to Image Classification: Contextualizing Progress on Benchmarks. Shibani Santurkar's 32 research works with 4,029 citations and 3,879 reads, including: Whose Opinions Do Language Models Reflect? Shibani Santurkar is an academic researcher from Massachusetts Institute of Technology. edu Shibani Santurkar is a researcher at OpenAI working in building safe and reliable machine learning models. [an error occurred while processing this directive] Shibani Santurkar is View a PDF of the paper titled Whose Opinions Do Language Models Reflect?, by Shibani Santurkar and 5 other authors Shibani Santurkar is on Facebook. edu Dimitris Tsipras MIT tsipras@mit. Shibani received a PhD in Computer Science from Whose Opinions Do Language Models Reflect?Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori Hashimoto Editing a classifier by rewriting its prediction rules Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Mądry December 2021NIPS '21: Proceedings of 301 Followers, 386 Following, 7 Posts - Shibani Santurkar (@shibanisanturkar) on Instagram: "" Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry Postdoc, Stanford University - Citado por 19,237 - Machine Learning. Specifically, my work revolves around: Affiliations: [Massachusetts Insititute of Technology]. i8hyc, uk54u, 1f3tg, c6yc5o, jr5azh, 2ud3, nzpla, k3stk7, jkcc, qlrd,