63 citations · 198 across the 19 of their papers we have counts for
20 papers
Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization
Tuo Liu, El Mehdi Saad, Wojciech Kotłowski +1
Dual averaging and gradient descent with their stochastic variants stand as the two canonical recipe books for first-order optimization: Every modern variant can be viewed as a des…
Confidence Sequences for Generalized Linear Models via Regret Analysis
Eugenio Clerico, Hamish Flynn, Wojciech Kotłowski +1
We develop a methodology for constructing confidence sets for parameters of statistical models via a reduction to sequential prediction. Our key observation is that for any general…
The CausalBench challenge: A machine learning contest for gene network inference from single-cell perturbation data
Mathieu Chevalley, Jacob Sackett-Sanders, Yusuf Roohani +15
In drug discovery, mapping interactions between genes within cellular systems is a crucial early step. Such maps are not only foundational for understanding the molecular mechanism…
Learning from Randomly Initialized Neural Network Features
Ehsan Amid, Rohan Anil, Wojciech Kotłowski +1
We present the surprising result that randomly initialized neural networks are good feature extractors in expectation. These random features correspond to finite-sample realization…
Robust Online Convex Optimization in the Presence of Outliers
Tim van Erven, Sarah Sachs, Wouter M. Koolen +1
We consider online convex optimization when a number k of data points are outliers that may be corrupted. We model this by introducing the notion of robust regret, which measures t…
A case where a spindly two-layer linear network whips any neural network with a fully connected input layer
Manfred K. Warmuth, Wojciech Kotłowski, Ehsan Amid
It was conjectured that any neural network of any structure and arbitrary differentiable transfer functions at the nodes cannot learn the following problem sample efficiently when…
Learning to Crawl
Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski +2
Web crawling is the problem of keeping a cache of webpages fresh, i.e., having the most recent copy available when a page is requested. This problem is usually coupled with the nat…
Adaptive scale-invariant online algorithms for learning linear models
Michał Kempka, Wojciech Kotłowski, Manfred K. Warmuth
We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function…
Bandit Principal Component Analysis
Wojciech Kotłowski, Gergely Neu
We consider a partial-feedback variant of the well-studied online PCA problem where a learner attempts to predict a sequence of -dimensional vectors in terms of a quadratic loss…
The Many Faces of Exponential Weights in Online Learning
Dirk van der Hoeven, Tim van Erven, Wojciech Kotłowski
A standard introduction to online learning might place Online Gradient Descent at its center and then proceed to develop generalizations and extensions like Online Mirror Descent a…
Scale-invariant unconstrained online learning
Wojciech Kotłowski
We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale inv…
Online Isotonic Regression
Wojciech Kotłowski, Wouter M. Koolen, Alan Malek
We consider the online version of the isotonic regression problem. Given a set of linearly ordered points (e.g., on the real line), the learner must predict labels sequentially at…
PCA with Gaussian perturbations
Wojciech Kotłowski, Manfred K. Warmuth
Most of machine learning deals with vector parameters. Ideally we would like to take higher order information into account and make use of matrix or even tensor parameters. However…
Surrogate regret bounds for generalized classification performance metrics
Wojciech Kotłowski, Krzysztof Dembczyński
We consider optimization of generalized performance metrics for binary classification by means of surrogate losses. We focus on a class of metrics, which are linear-fractional func…
Consistent optimization of AMS by logistic loss minimization
Wojciech Kotłowski
In this paper, we theoretically justify an approach popular among participants of the Higgs Boson Machine Learning Challenge to optimize approximate median significance (AMS). The…
On-line PCA with Optimal Regrets
Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth
We carefully investigate the on-line version of PCA, where in each trial a learning algorithm plays a k-dimensional subspace, and suffers the compression loss on the next instance…
Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families
Peter Bartlett, Peter Grunwald, Peter Harremoes +2
We study online learning under logarithmic loss with regular parametric models. Hedayati and Bartlett (2012b) showed that a Bayesian prediction strategy with Jeffreys prior and seq…
Consistent Multilabel Ranking through Univariate Losses
Krzysztof Dembczynski, Wojciech Kotlowski, Eyke Huellermeier
We consider the problem of rank loss minimization in the setting of multilabel classification, which is usually tackled by means of convex surrogate losses defined on pairs of labe…
Quantum learning: optimal classification of qubit states
Madalin Guta, Wojciech Kotlowski
Pattern recognition is a central topic in Learning Theory with numerous applications such as voice and text recognition, image analysis, computer diagnosis. The statistical set-up…
Prequential Plug-In Codes that Achieve Optimal Redundancy Rates even if the Model is Wrong
Peter Grünwald, Wojciech Kotłowski
We analyse the prequential plug-in codes relative to one-parameter exponential families M. We show that if data are sampled i.i.d. from some distribution outside M, then the redund…