Colloquia and Seminars

To join the email distribution list of the cs colloquia, please visit the list subscription page.


Computer Science events calendar in HTTP ICS format for of Google calendars, and for Outlook.

Academic Calendar at Technion site.

Upcoming Colloquia & Seminars

  • Hypernetworks and a New Feedback Model

    Speaker:
    Lior Wolf - COLLOQUIUM LECTURE - CANCELLED
    Date:
    Tuesday, 31.3.2020, 14:30
    Place:
    Room 337 Taub Bld.
    Affiliation:
    School of Computer Science, Tel-Aviv University
    Host:
    Yuval Filmus

    Hypernetworks, also known as dynamic networks, are neural networks in which the weights of at least some of the layers vary dynamically based on the input. Such networks have composite architectures in which one network predicts the weights of another network. I will briefly describe the early days of dynamic layers and present recent results from diverse domains: 3D reconstruction from a single image, image retouching, electrical circuit design, decoding block codes, graph hypernetworks for bioinformatics, and action recognition in video. Finally, I will present a new hypernetwork-based model for the role of feedback in neural computations. Short Bio: ========== Lior Wolf is a faculty member at the School of Computer Science at Tel Aviv University and a research scientist at Facebook AI Research. Before, he was a postdoc working with Prof. Poggio at CBCL, MIT. He received his PhD working with Prof. Shashua at the Hebrew U, Jerusalem. ====================================== Refreshments will be served from 14:15 Lecture starts at 14:30

  • Date:
    Place:
  • Date:
    Place:
  • Algorithms for Two-Player Turn-Based Stochastic Games

    Speaker:
    Uri Zwick - COLLOQUIUM LECTURE- CANCELLED
    Date:
    Tuesday, 7.4.2020, 14:30
    Place:
    Room 337 Taub Bld.
    Affiliation:
    Dept. of Computer Science - Tel-Aviv University
    Host:
    Yuval Filmus

    Two-player turn-based zero-sum stochastic games is an interesting family of infinite duration games played on a finite set of states. These games may be seen as an extension of Markov Decisions Processes (MDPs) to a two-player setting. Such games have applications in various areas ranging from Artificial Intelligence, Operations Research and Automatic Verification. From the theoretical point of view they are interesting because they are known to be in NP intersection co-NP, yet no polynomial time algorithm is known for their solution. They also belong to the complexity classes PLS, PPAD and CLS, but are not known to be complete in then. The talk will survey known algorithmic approaches for solving such games, as well as restricted families of games such as Mean Payoff Games (MPGs) and Parity Games (PGs). Short Bio: ========== Uri Zwick has worked on graph algorithms, in particular on distances in graphs and on the color-coding technique for subgraph isomorphism. With Howard Karloff, he is the namesake of the Karloff-Zwick algorithm for approximating the MAX-3SAT problem of Boolean satisfiability. He and his coauthors have won the David P. Robbins Prize in 2011 for their work on the block-stacking problem. Zwick earned a bachelor's degree from the Technion, and completed his doctorate at Tel Aviv University in 1989 under the supervision of Noga Alon. He is currently a professor of computer science at Tel Aviv University. ===================== Rereshments will be served from 14:15 Lecture starts at 14:30

  • Date:
    Place:
  • Date:
    Place:
  • Second-order Optimization for Machine Learning, Made Practical

    Speaker:
    Tomer Koren - COLLOQUIUM LECTURE
    Date:
    Tuesday, 5.5.2020, 14:30
    Place:
    Room 337 Taub Bld.
    Affiliation:
    School of Computer Science at Tel Aviv University
    Host:
    Yuval Filmus

    Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods---that involve second-order derivatives and/or second-order statistics of the data---have become far less prevalent despite strong theoretical properties, due to their impractical computation, memory and communication costs. I will present some recent theoretical, algorithmic and infrastructural advances that allow for overcoming these challenges in using second-order methods and obtaining significant performance gains in practice, at very large scale, and on highly-parallel computing architectures. Short Bio: =========== Tomer Koren is an Assistant Professor in the School of Computer Science at Tel Aviv University since Fall 2019. Previously, he was a Senior Research Scientist at Google Brain, Mountain View. He received his PhD in December 2016 from the Technion - Israel Institute of Technology, where his advisor was Prof. Elad Hazan. His research interests are in machine learning and optimization. ===================================== Rereshments will be served from 14:15 Lecture starts at 14:30