activity
20112021
most citedDiscrepancy Skew Products and Affine Random Walks

5 citations · 10 across the 8 of their papers we have counts for

collaborators

10 papers

cs.LG2021

Uniform Generalization Bounds for Overparameterized Neural Networks

Sattar Vakili, Michael Bromberg, Jezabel Garcia +2

An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the clas…

cs.LG2021

How to distribute data across tasks for meta-learning?

Alexandru Cioba, Michael Bromberg, Qian Wang +5

Meta-learning models transfer the knowledge acquired from previous tasks to quickly learn new ones. They are trained on benchmarks with a fixed number of data points per task. This…

cs.CV2020

Cyclic orthogonal convolutions for long-range integration of features

Federica Freddi, Jezabel R Garcia, Michael Bromberg +4

In Convolutional Neural Networks (CNNs) information flows across a small neighbourhood of each pixel of an image, preventing long-range integration of features before reaching deep…

math.DS2017

A temporal Central Limit Theorem for real-valued cocycles over rotations

Michael Bromberg, Corinna Ulcigrai

We consider deterministic random walks on the real line driven by irrational rotations, or equivalently, skew product extensions of a rotation by where the skewing cocycle is a…

math.DS2017

Rational ergodicity of Step function Skew Products

Jon. Aaronson, Michael Bromberg, Nishant Chandgotia

We study rational step function skew products over certain rotations of the circle proving ergodicity and bounded rational ergodicity when rotation number is a quadratic irrational…

math.DS2016★ 5 cited

Discrepancy Skew Products and Affine Random Walks

Jon. Aaronson, Michael Bromberg, Hitoshi Nakada

We prove bounded rational ergodicity for some discrepancy skew products whose rotation number has bad rational approximation. This is done by considering the asymptotics of associa…

math.DS2015★ 1 cited

Ergodic Properties of the Random Walk Adic Transformation over the Beta Transformation

Michael Bromberg

We define a random walk adic transformation associated to an aperiodic random walk on driven by a -transformation and study its ergodic…

math.DS2015

Invariance principle for local time by quasi-compactness

Michael Bromberg

The objective of this paper is to prove a functional weak invariance principle for a local time of a process of the form where …

math.DS2014★ 3 cited

Weak invariance principle for the local times of Gibbs-Markov processes

Michael Bromberg

The subject of this paper is to prove a functional weak invariance principle for the local time of a process generated by a Gibbs-Markov map. More precisely, let $\left(X,\mathcal{…

math.PR2011★ 1 cited

Weak invariance principle for the local times of partial sums of Markov Chains

Michael Bromberg, Zemer Kosloff

Let X_{n} be an integer valued Markov Chain with finite state space. Let S_{n}=\sum_{k=0}^{n}X_{k} and let L_{n}(x) be the number of times S_{k} hits x up to step n. Define the nor…