Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Gerber, Patrik"'
Autor:
Gerber, Patrik Róbert
This thesis studies questions in nonparametric testing and estimation that are inspired by machine learning. One of the main problems of our interest is likelihood-free hypothesis testing: given three samples X, Y and Z with sample sizes n, n and m r
Externí odkaz:
https://hdl.handle.net/1721.1/155358
We propose a new density estimation algorithm. Given $n$ i.i.d. samples from a distribution belonging to a class of densities on $\mathbb{R}^d$, our estimator outputs any density in the class whose ''perceptron discrepancy'' with the empirical distri
Externí odkaz:
http://arxiv.org/abs/2312.17701
Given $n$ observations from two balanced classes, consider the task of labeling an additional $m$ inputs that are known to all belong to \emph{one} of the two classes. Special cases of this problem are well-known: with complete knowledge of class dis
Externí odkaz:
http://arxiv.org/abs/2308.09043
This paper considers an ML inspired approach to hypothesis testing known as classifier/classification-accuracy testing ($\mathsf{CAT}$). In $\mathsf{CAT}$, one first trains a classifier by feeding it labeled synthetic samples generated by the null an
Externí odkaz:
http://arxiv.org/abs/2306.11085
Consider the problem of binary hypothesis testing. Given $Z$ coming from either $\mathbb P^{\otimes m}$ or $\mathbb Q^{\otimes m}$, to decide between the two with small probability of error it is sufficient, and in many cases necessary, to have $m\as
Externí odkaz:
http://arxiv.org/abs/2211.01126
We prove two lower bounds for the complexity of non-log-concave sampling within the framework of Balasubramanian et al. (2022), who introduced the use of Fisher information (FI) bounds as a notion of approximate first-order stationarity in sampling.
Externí odkaz:
http://arxiv.org/abs/2210.02482
We introduce a novel relaxation of combinatorial discrepancy called Gaussian discrepancy, whereby binary signings are replaced with correlated standard Gaussian random variables. This relaxation effectively reformulates an optimization problem over t
Externí odkaz:
http://arxiv.org/abs/2109.08280
We study first-order optimization algorithms for computing the barycenter of Gaussian distributions with respect to the optimal transport metric. Although the objective is geodesically non-convex, Riemannian GD empirically converges rapidly, in fact
Externí odkaz:
http://arxiv.org/abs/2106.08502
We consider the task of generating exact samples from a target distribution, known up to normalization, over a finite alphabet. The classical algorithm for this task is rejection sampling, and although it has been used in practice for decades, there
Externí odkaz:
http://arxiv.org/abs/2105.14166
We establish the first tight lower bound of $\Omega(\log\log\kappa)$ on the query complexity of sampling from the class of strongly log-concave and log-smooth distributions with condition number $\kappa$ in one dimension. Whereas existing guarantees
Externí odkaz:
http://arxiv.org/abs/2105.14163