Publications associées à Proximal Point Imitation Learning

Convex optimization in sums of Banach spaces

We characterize the solution of a broad class of convex optimization problems that address the reconstruction of a function from a finite number of linear measurements. The underlying hypothesis is that the solution is decomposable as a finite sum of compo ...

2021

A first-order primal-dual method with adaptivity to local smoothness

Volkan Cevher, Maria-Luiza Vladarean

We consider the problem of finding a saddle point for the convex-concave objective

\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y)

, where

f

is a convex function with locally Lipschitz gradient and

g

is convex and possibly non-smooth. We propose an ...

2021

Poly-NL: Linear Complexity Non-local Layers With 3rd Order Polynomials

Grigorios Chrysos, Filippos Kokkinos

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions. Such pairwise functions underpin the effectiveness of non-lo ...

IEEE2021

Functional Inverse Problems on Spheres: Theory, Algorithms and Applications

Matthieu Martin Jean-André Simeoni

Many scientific inquiries in natural sciences involve approximating a spherical field -namely a scalar quantity defined over a continuum of directions- from generalised samples of the latter (e.g. directional samples, local averages, etc). Such an approxim ...

EPFL2020

On Gaussian Process based Koopman Operator

Colin Neil Jones

Enabling analysis of non-linear systems in linear form, the Koopman operator has been shown to be a powerful tool for system identification and controller design. However, current data-driven methods cannot provide quantification of model uncertainty given ...

2020

Matrix recovery from bilinear and quadratic measurements

Martin Vetterli, Adam James Scholefield, Michalina Wanda Pacholska, Karen Adam

Matrix (or operator) recovery from linear measurements is a well-studied problem. However, there are situations where only bilinear or quadratic measurements are available. A bilinear or quadratic problem can easily be transformed into a linear one, but it ...

ArXiv2020

Adaptive Gradient Descent without Descent

Konstantin Mishchenko

We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don’t increase the stepsize too fast and 2) don’t overstep the local curvature. No need for functional values, no line search, no information about the func ...

2020

Learning Activation Functions in Deep (Spline) Neural Networks

Michaël Unser, Pakshal Narendra Bohra, Shayan Aziznejad, Harshit Gupta, Joaquim Gonçalves Garcia Barreto Campos

We develop an efficient computational solution to train deep neural networks (DNN) with free-form activation functions. To make the problem well-posed, we augment the cost functional of the DNN by adding an appropriate shape regularization: the sum of the ...

2020

A stability theory beyond the co-rotational setting for critical wave maps blow up

Joachim Krieger, Shuang Miao

We exhibit non-equivariant perturbations of the blowup solutions constructed in [18] for energy critical wave maps into

\mathbb{S}^2

. Our admissible class of perturbations is an open set in some sufficiently smooth topology and vanishes near the light co ...

2020

Deep Spline Networks With Control Of Lipschitz Regularity

Michaël Unser, Shayan Aziznejad

The motivation for this work is to improve the performance of deep neural networks through the optimization of the individual activation functions. Since the latter results in an infinite-dimensional optimization problem, we resolve the ambiguity by search ...

IEEE2019

Proximal Point Imitation Learning

Graph Chatbot

Chattez avec Graph Search

Convex optimization in sums of Banach spaces

A first-order primal-dual method with adaptivity to local smoothness

Poly-NL: Linear Complexity Non-local Layers With 3rd Order Polynomials

Functional Inverse Problems on Spheres: Theory, Algorithms and Applications

On Gaussian Process based Koopman Operator

Matrix recovery from bilinear and quadratic measurements

Adaptive Gradient Descent without Descent

Learning Activation Functions in Deep (Spline) Neural Networks

A stability theory beyond the co-rotational setting for critical wave maps blow up

Deep Spline Networks With Control Of Lipschitz Regularity

A first-order primal-dual method with adaptivity to local smoothness

A stability theory beyond the co-rotational setting for critical wave maps blow up

Convex optimization in sums of Banach spaces

Learning Activation Functions in Deep (Spline) Neural Networks

Functional Inverse Problems on Spheres: Theory, Algorithms and Applications

Matrix recovery from bilinear and quadratic measurements

On Gaussian Process based Koopman Operator

Poly-NL: Linear Complexity Non-local Layers With 3rd Order Polynomials

Adaptive Gradient Descent without Descent

Deep Spline Networks With Control Of Lipschitz Regularity