December 2011
9 posts
How to conduct your own annual review →
Large deviations for the local fluctuations of random walks and new insights into the “randomness” of Pi http://arxiv.org/abs/1004.3713v2
Active Learning Halfspaces under Margin Assumptions http://arxiv.org/abs/1112.1556v1
Predictors for time series with energy decay on higher frequencies http://arxiv.org/abs/1112.1478v1
Information-Theoretically Optimal Compressed Sensing via Spatial Coupling and Approximate Message Passing http://arxiv.org/abs/1112.0708v1
On the question of effective sample size in network modeling http://arxiv.org/abs/1112.0840v1
2 tags
Dimension adaptability of Gaussian process models...
http://arxiv.org/abs/1112.0716v1
2 tags
Multi-stage Convex Relaxation for Feature Selection http://arxiv.org/abs/1106.0565v2
2 tags
Machine learning with operational costs
http://arxiv.org/abs/1112.0698v1
October 2011
0 posts
Model Selection in Reinforcement Learning
Csaba Szepesvári and I have a new paper about the model selection problem in reinforcement learning. This paper, which is published by the Machine Learning Journal, considers the batch (offline, non-interactive) reinforcement learning setting when the goal is to find an action-value function with the smallest Bellman error among a countable set of candidate functions. We prove an oracle-like...
Theoretical Computer Science Cheat sheet →
Includes Order notation, Series, Combinatorics, Recurrences, Probability, Trigonometric, Calculus, Series expansion, and many other things.
July 2010
2 posts
The Three Golden Rules for Successful Scientific... →
by Dijkstra.
GRASP Lecture Series →
June 2010
3 posts
1 tag
Approximate Dynamic Programming via Iterated... →
By Wang and Boyd.
A Course on Convex Optimization →
By Stephen Boyd.
Workshop on Simulation Optimization →
April 2010
1 post
1 tag
Stability Bounds for Stationary phi and... →
JMLR 2010 paper by Mehryar Mohri and Afshin Rostamizadeh.
March 2010
1 post
1 tag
Stochastic Optimization (James Spall) →
Talks about SPSA, FDSA, and GA.
January 2010
1 post
Sam Roweis died
So sad that such an energetic and nice person perishes this way.
December 2009
1 post
Ray Solomonoff (1926 - 2009)
Ray Solomonoff passed away last week.
October 2009
5 posts
Processing →
“Processing is an open source programming language and environment for people who want to program images, animation, and interactions.”
1 tag
Model Selection Homepage →
Ph.D. Candidate!
I am a Ph.D. candidate since 16:30 today! Hurray!
“Focusing on important questions puts us in the awkward position of being...”
– The importance of stupidity in scientific research by Martin A. Schwartz.
How to Publish in Top Journals →
by Kwan Choi.
September 2009
3 posts
1 tag
Unlabeled data: Now it helps, now it doesn’t →
by Aarti Singh, Robert Nowak, and Xiaojin Zhu.
1 tag
1 tag
Relations between Probability Distributions
Distributions diagrams (also this article by Leemis and McQuestion)
Conjugate Priors (also Compendium of Conjugate Priors by Daniel Fink)
(credit: I found these links here.)
August 2009
6 posts
Sobolev Embedding Theorems, Besov Spaces, etc.
First we need the definition of Hölder and Sobolev spaces (Wikipedia).
The idea of Hölder spaces is that the k-th derivative of the functions are alpha-Lipschitz. The idea of Sobolev spaces is that the k-th derivate of the functions are in Lp space.
Then we have different Sobolev inequalities. These inequalities basically say which Sobolev space can be embedded in another one. Of course, if two...
1 tag
Generalized Representer Theorem
Scholkopf, Herbrich, Smola, “Generalized Representer Theorem”.
The theorem is quite general: for an arbitrary loss function L(.) that depends on data x_1,…,x_m, and regularizer in the form of g(||f||) with g(.) as strictly monotonic increasing, we have the usual expansion in the form of f(.) = \sum_{i=1}^m a_i k(.,x_i) .
Also the Remark 6, biased regularization, is quite...
2 tags
Homepage of K. Avrachenkov →
Perturbation theory for Markov Chains
1 tag
Fixed point theorems in infinite-dimensional... →
from Wikipedia.
Take a look at Schauder fixed-point theorem too.
1 tag
Some presentations from Yousef Saad on... →
Interesting!
1 tag
Cubic regularization of Newton method and its... →
By Nesterov and Polyak.
July 2009
1 post
Research productivity: some paths less travelled (Brian Martin)
http://www.uow.edu.au/arts/sts/bmartin/pubs/09aur.html
May 2009
2 posts
Advices to a Young Mathematician →
1 tag
Inequalities for the L1 deviations of the... →
by Weissman, Ordentlich, Seroussi, Verdu, Weinberger.
March 2009
5 posts
2 tags
On Fast Rates in Classification
I am wondering what types of regularities are natural to be used in classification problems. In regression setting, different notion of smoothness appears naturally in the bound. I was wondering if I could find similar results for classification.
The field’s landscape is not clear to me yet. People use margin noise conditions that may give them fast rates (faster than n^{-1/2}). If their...
2 tags
Rapid Mixing in Markov Chains →
By R. Kannan.
2 tags
Reliable Reason: Induction and Statistical... →
A book by Gilbert Harman and Sanjeev Kulkarni on philosophy of science - an STL approach.
1 tag
On Pattern Theory (David Mumford)
David Mumford, “Empirical Statistics and Stochastic Models for Visual Signals”.
David Mumford, “Pattern Theory: the Mathematics of Perception” (presentation slides)
1 tag
How to Compare Different Loss Functions and Their... →
by Ingo Steinwart.
February 2009
5 posts
2 tags
Evolutionary Epistemology (EET and EEM) →
1 tag
Conditional Density Estimation
Chen, Linton and Robinson, “The Estimation of Conditional Densities”. (some interesting results regarding the mixing properties for Markov models)
Hansen, “Nonparametric Conditional Density Estimation,” 2004. (Two-stage method for conditional density estimation: estimate the mean, and then estimate the deviation from the mean)
Yoon, “Bayesian Conditional Density...
1 tag
A few papers by Terrence J. Sejnowski
L. Finelli and T. Sejnowski, “What is Consolidated During Sleep-Dependent Motor Skill Learning?,” 2005.
T. Flash and T. Sejnowski, “Computational Approaches to Motor Control,” 2001.
D. Garlick and T. Sejnowski, “There is more to Fluid Intelligence than Working Memory Capacity and Executive Function,” 2006.
T. Sejnowski, “Sleep and Memory,” 1995.
1 tag
Yuhong Yang →
2 tags
A Few Papers on ADP and etc from Bertsekas et al.
H. Yu and D. Bertsekas, Basis Function Adaptation Methods for Cost Approximation in MDP, 2009.
H. Yu and D. Bertsekas, New Error Bounds for Approximations from Projected Linear Equations, 2008.
H. Yu and D. Bertsekas, A Least Squares Q-Learning Algorithm for Optimal Stopping Problems, 2006.
D. Bertsekas, Dynamic Programming and Suboptimal Control: A Survey from ADP to MPC, 2005.
D. Bertsekas,...
January 2009
5 posts
Mathematical Issues in Dynamic Programming →
by Dimitri Bertsekas and Steven Shreve.
Talks about the measurability problems one may face when he wants to deal with uncountable state spaces.
3 tags
Stochastic Approximation: A Dynamical Systems... →
A book by Vivek S. Borkar.
Thanks to Francisco Melo for the pointer.
1 tag
Active Learning Literature Survey →
by Burr Settles.