Exponential Natural Evolution Strategies

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

A key challenge across many disciplines is to extract meaningful information from data which is often obscured by noise. These datasets are typically represented as large matrices. Given the current trend of ever-increasing data volumes, with datasets grow ...

We consider the problem of finding a basis of a matroid with weight exactly equal to a given target. Here weights can be discrete values from

\{-\Delta,\ldots,\Delta\}

or more generally

m

-dimensional vectors of such discrete values. We resolve the para ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

Multiple tensor-times-matrix (Multi-TTM) is a key computation in algorithms for computing and operating with the Tucker tensor decomposition, which is frequently used in multidimensional data analysis. We establish communication lower bounds that determine ...

In this paper, we present a new parameterization and optimization procedure for minimizing the weight of ribbed plates. The primary goal is to reduce embodied CO2 in concrete floors as part of the effort to diminish the carbon footprint of the construction ...

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

In the field of choice modeling, the availability of ever-larger datasets has the potential to significantly expand our understanding of human behavior, but this prospect is limited by the poor scalability of discrete choice models (DCMs): as sample sizes ...

In Process Systems Engineering, computationally-demanding models are frequent and plentiful. Handling such complexity in an optimization framework in a fast and reliable way is essential, not only for generating meaningful solutions but also for providing ...

A geometric method of lattice reduction based on cycles of directional and hyperplanar shears is presented. The deviation from cubicity at each step of the reduction is evaluated by a parameter called 'basis rhombicity' which is the sum of the absolute val ...

We consider the Dynamical Low Rank (DLR) approximation of random parabolic equations and propose a class of fully discrete numerical schemes. Similarly to the continuous DLR approximation, our schemes are shown to satisfy a discrete variational formulation ...

Exponential Natural Evolution Strategies

Chat with Graph Search

Gibbs sampling the posterior of neural networks

Spectral Estimators for High-Dimensional Matrix Inference

Sensitivity, Proximity and FPT Algorithms for Exact Matroid Problems

Deep Learning Theory Through the Lens of Diagonal Linear Networks

COMMUNICATION LOWER BOUNDS AND OPTIMAL ALGORITHMS FOR MULTIPLE TENSOR-TIMES-MATRIX COMPUTATION

Mesh-based topology, shape and sizing optimization of ribbed plates

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Stochastic adaptive resampling for the estimation of discrete choice models

A combined genetic algorithm and active learning approach to build and test surrogate models in Process Systems Engineering

A new method for lattice reduction using directional and hyperplanar shearing

Stability properties of a projector-splitting scheme for dynamical low rank approximation of random parabolic equations