paper-with-me

홈 › Papers

How Could Polyhedral Theory Harness Deep Learning?

2018-06-17 · Thiago Serra, Christian Tjandraatmadja, Srikumar Ramalingam

The holy grail of deep learning is to come up with an automatic method to design optimal architectures for different applications. In other words, how can we effectively dimension and organize neurons along the network layers based on the computational resources, input size, and amount of training data? We outline promising research directions based on polyhedral theory and mixed-integer representability that may offer an analytical approach to this question, in contrast to the empirical techniques often employed.

📄 PDF Abstract BibTeX arXiv:1806.06365

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Combinatorial Regularity for Relatively Perfect Discrete Morse Gradient Vector Fields of ReLU Neural Networks

2024-12-23 · Robyn Brooks, Marissa Masden

One common function class in machine learning is the class of ReLU neural networks. ReLU neural networks induce a piecewise linear decomposition of their input space called the canonical polyhedral complex. It has previo…

Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space

2023-12-05 · Yiheng Jiang, Sinho Chewi, Aram-Alexandre Pooladian

We develop a theory of finite-dimensional polyhedral subsets over the Wasserstein space and optimization of functionals over them via first-order methods. Our main application is to the problem of mean-field variational …

Variational Inference

On the convex hull of convex quadratic optimization problems with indicators

2022-01-02 · Linchuan Wei, Alper Atamtürk, Andrés Gómez, Simge Küçükyavuz

We consider the convex quadratic optimization problem with indicator variables and arbitrary constraints on the indicators. We show that a convex hull description of the associated mixed-integer set in an extended space …

Principled Deep Neural Network Training through Linear Programming

2018-10-07 · ICLR 2019 5 · Daniel Bienstock, Gonzalo Muñoz, Sebastian Pokutta

Deep learning has received much attention lately due to the impressive empirical performance achieved by training algorithms. Consequently, a need for a better theoretical understanding of these problems has become more …

Random Polyhedral Scenes: An Image Generator for Active Vision System Experiments

2018-03-27 · Markus D. Solbach, Stephen Voland, Jeff Edmonds, John K. Tsotsos

We present a Polyhedral Scene Generator system which creates a random scene based on a few user parameters, renders the scene from random view points and creates a dataset containing the renderings and corresponding anno…