A Research Blog
Blake Bordelon, Haozhe Shan, Abdul Canatar, Boaz Barak, Cengiz Pehlevan See part 1 of this series, and pdf version of both parts. See also all seminar posts. In the previous post we described the outline of the replica method, and outlined the analysis per this figure: Specifically, we reduced the task of evaluating the expectation … Continue reading Replica Method for the Machine Learning Theorist: Part 2 of 2
Blake Bordelon, Haozhe Shan, Abdul Canatar, Boaz Barak, Cengiz Pehlevan [Boaz's note: Blake and Haozhe were students in the ML theory seminar this spring; in that seminar we touched on the replica method in the lecture on inference and statistical physics but here Blake and Haozhe (with a little help from the rest of us) … Continue reading Replica Method for the Machine Learning Theorist: Part 1 of 2
The second edition of the recently created conference on Information-Theoretic Cryptography (ITC 2021) will take place virtually on July 24-26, 2021. The final program is out and contains exciting new works and invited talks that highlight the recent advances in the area by Benny Applebaum, Elaine Shi, Irit Dinur, Salman Avestimehr, Matthieu Bloch, and Mark … Continue reading ITC 2021: Call for participation (guest post by Benny Applebaum)
The 53rd Annual ACM Symposium on Theory of Computing (STOC'21) concludes today, after 5 days of action-packed, Gather-power talks, workshops, plenary talks, and posters. A huge thank you to all volunteers, organizers, speakers, and attendees, who helped make this virtual conference a success! We would like to ask for your feedback on the conference. Whether … Continue reading STOC feedback and TCS Wikipedia (guest post by Clément Canonne )
[H/T Jelani Nelson] In recent years there has been increasing interest in using machinelearning to improve the performance of classical algorithms incomputer science, by fine-tuning their behavior to adapt to theproperties of the input distribution. This “data-driven” or“learning-based” approach to algorithm design has the potential tosignificantly improve the efficiency of some of the most widely … Continue reading Machine Learning for Algorithms – virtual workshop
Scribe notes by Junu Lee, Yash Nair, and Richard Xu. Previous post: Toward a theory of generalization learning Next post: TBD. See also all seminar posts and course webpage. lecture slides (pdf) - lecture slides (Powerpoint with animation and annotation) - video Much of the material on causality is taken from the wonderful book by … Continue reading Causality and Fairness
The Simons institute started a new virtual seminar series highlighting recent advances in theoretical computer science. The first two talks in the series will be: June 16th 10am-11am PDT (1pm-2pm EDT). Virginia Vassilevska Williams on a Refined Laser Method and Faster Matrix MultiplicationAugust 5 10am-11am PDT (1pm-2pm EDT) Yuansi Chen on An Almost Constant Lower … Continue reading New seminar series in Simons Institute
The fifth WOLA (Workshop on Local Algorithms) will be virtual, and take place June 14-15. Registration is free, but required: please fill this form by June 10th to attend. Local algorithms — that is, algorithms that compute and make decisions on parts of the output considering only a portion of the input — have been studied in a number of … Continue reading Workshop on Local Algorithms (Guest post by Ronitt Rubinfeld)
A reminder: the deadline to submit nominations for the STOC Test of Time Award is May 24. You can nominate papers for the 10 year award - STOC 2007-201120 year award - STOC 1997-200130 year award - STOC 1987-1991The award website ( https://sigact.org/prizes/stoc_tot.html ) helpfully contains links to the papers published in all these conferences. … Continue reading STOC Test of time award
[Guest post from Pranjal Awasthi and Rina Panigrahy - workshop looks great! --Boaz] Please join us for a virtual Google workshop on “Conceptual Understanding of Deep Learning” When: May 17th 9am-4pm. Where: Live over Youtube, Goal: How does the Brain/Mind (perhaps even an artificial one) work at an algorithmic level? While deep learning has produced tremendous technological … Continue reading Google Research Workshop on Deep Learning Theory
Windows On Theory 