Avrim Blum is speaking at 3:00 on October 8. The talk is entitled "Towards theoretical models of natural inputs: aiming to bridge the Theory/AI divide"
Tuesday, March 26th at 3:00pm, Daniel Hsu (Microsoft Research) will give a talk "Fast learning algorithms for discovering the hidden structure in data" in Wu & Chen Auditorium, 101 Levine Hall
Wednesday, March 27 at 4:30pm, Martin Wainwright (UC Berkeley) will give a talk "High-dimensional marginalization on graphs: Stochastic message-passing with quantitative guarantees" in F60 JMHH.
Monday, April 1st at 1:30pm, Nina Balcan is giving a talk "Learning Valuation Functions" in Levine 512.
Wednesday, September 19th at 4:30, Lorenzo Rosasco (MIT/IIT) will give a talk "On Learning Data Representations" in F50 JMHH.
PRiML is co-sponsoring a symposium honoring Vladimir Vapnik who received the 2012 Benjamin Franklin Medal in Computer and Cognitive Science, featuring talks by Michael Jordan, Michael Kearns and Robert Schapire. The event will take place on Wednesday April 25, from 10AM to 3PM in Berger Auditorium, Skirkanich Hall.
Monday, March 12 at noon, Tamir Hazan will give a talk on 'Estimating the Partition Function with Random Maximum A-Posteriori Perturbations', in Levine 315.
Tuesday, January 17th at 4:30, Ohad Shamir (MSR) will give a talk "From Bandits to Experts: On the Value of Side-Observations" in F65 JMHH.
Wednesday, February 15th at 4:30, David McAllester will give a talk on: "Generalization Bounds and Consistency for Latent-Structural Probit and Ramp Loss"
- PRiML@NYAS ML Day: Our students Jenny Gillenwater and Alex Kulesza won second place best paper award at the 6th Annual Machine Learning Symposium at the New York Academy of Sciences on October 21, 2011!
- Sasha Rakhlin and his co-authors (Karthik Sridharan and Ambuj Tewari) received the Best Paper Award at COLT 2011.
- Ben Taskar received the NSF CAREER award for his research on Computation and Approximation in Structured Learning.
- PRiML@NYAS ML Day: Our students won three out of the four best student paper awards at the 5th Annual Machine Learning Symposium at the New York Academy of Sciences on October 22, 2010! The winning papers from PRiML were:
1. "Parametric Bandits, Query Learning, and the Haystack Dimension", by Kareem Amin, Michael Kearns and Umar Syed
3. "Structured Determinantal Point Processes", by Alex Kulesza and Ben Taskar
4. "Posterior Sparsity in Dependency Grammar Induction", by Jennifer Gillenwater, Kuzman Ganchev, Joao Graša, Fernando Pereira, and Ben Taskar
- Congratulations to Kuzman Ganchev! Kuzman (co-advised by Fernando Pereira and Ben Taskar) was selected as the runner-up for the John Atanasoff Award from the President of the Republic of Bulgaria. This award is given annually to a Bulgarian scientist under 35 for scientific or practical contributions to the development of computer and information technology worldwide and significant economic or social importance for Bulgaria. Details in English
- Kick-off Colloquium was held on October 1, 2010, 1pm-7pm in Wu & Chen Auditorium, Levine Hall. The colloquium featured Carlos Guestrin, Rob Schapire, Mehryar Mohri and Michael Littman as invited speakers, PRiML faculty talks and student posters.
- Call for papers: NIPS 2010 Workshop on Coarse-to-Fine Learning and Inference, organized by Slav Petrov, Ben Sapp, Ben Taskar, David Weiss. Due date: October 29th.
- PRiML@NIPS: Our faculty, postdocs and students have 9 papers this coming NIPS (2 orals, 2 spotlights, 5 posters):
Learning via Gaussian Herding, K. Crammer and D. D. Lee
Generative Local Metric Learning for Nearest Neighbor Classification, Y. K. Noh, B. T. Zhang, and D. D. Lee
Online Learning: Random Averages, Combinatorial Parameters and Learnability, A. Rakhlin, K. Sridharan, and A. Tewari
Random Walk Approach to Regret Minimization, H. Narayanan and A. Rakhlin
Learning from Logged Implicit Exploration Data, Alexander Strehl, John Langford, Lihong Li, Sham Kakade
A reduction from apprenticeship learning to classification, Umar Syed and Robert E. Schapire
Semi-Supervised Learning with Adversarially Missing Label Information, Umar Syed and Ben Taskar
Structured Determinantal Point Processes, Alex Kulesza and Ben Taskar
Tracking Complex Dynamics with Structured Prediction Cascades, David Weiss, Ben Sapp, Ben Taskar
- Sasha Rakhlin has received the NSF CAREER award for his research, "Statistical and Computational Complexities of Modern Learning Problems".
- Ben Taskar was awarded the Sloan Research Fellowship and selected for the ONR Young Investigator Program.
- Sham Kakade and his co-authors (Daniel Hsu, John Langford and Tong Zhang) received an Honorable Mention for Outstanding Student Paper Awards at the NIPS conference for their paper: ``Multi-Label Prediction via Compressed Sensing''.
- Sasha Rakhlin and his co-authors (J. Abernethy and E. Hazan) won the IBM Research 2008 Pat Goldberg Memorial Best Paper Award in CE, EE and Math for their paper ``Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization''
- The paper ``Censored Exploration and the Dark Pool Problem'' by Kuzman Ganchev, Michael Kearns, Yuriy Nevmyvaka and Jennifer Wortman received best student paper award at the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI 2009).