paper-with-me

Papers

Dual Convexified Convolutional Neural Networks

2022-05-27 · Site Bai, Chuyang Ke, Jean Honorio

We propose the framework of dual convexified convolutional neural networks (DCCNNs). In this framework, we first introduce a primal learning problem motivated by convexified convolutional neural networks (CCNNs), and then construct the dual convex training program through careful analysis of the Karush-Kuhn-Tucker (KKT) conditions and Fenchel conjugates. Our approach reduces the computational overhead of constructing a large kernel matrix and more importantly, eliminates the ambiguity of factorizing the matrix. Due to the low-rank structure in CCNNs and the related subdifferential of nuclear norms, there is no closed-form expression to recover the primal solution from the dual solution. To overcome this, we propose a highly novel weight recovery algorithm, which takes the dual solution and the kernel information as the input, and recovers the linear weight and the output of convolutional layer, instead of weight parameter. Furthermore, our recovery algorithm exploits the low-rank structure and imposes a small number of filters indirectly, which reduces the parameter size. As a result, DCCNNs inherit all the statistical benefits of CCNNs, while enjoying a more formal and efficient workflow.

📄 PDF Abstract BibTeX arXiv:2205.14056

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Convexified Convolutional Neural Networks

2016-09-04 · ICML 2017 8 · Yuchen Zhang, Percy Liang, Martin J. Wainwright

We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as …

Denoising

A Convexified Matching Approach to Imputation and Individualized Inference

2024-07-07 · YoonHaeng Hur, Tengyuan Liang

We introduce a new convexified matching method for missing value imputation and individualized inference inspired by computational optimal transport. Our method integrates favorable features from mainstream imputation ap…

counterfactualImputation

Adversarial Combinatorial Semi-bandits with Graph Feedback

2025-02-26 · Yuxiao Wen

In combinatorial semi-bandits, a learner repeatedly selects from a combinatorial decision set of arms, receives the realized sum of rewards, and observes the rewards of the individual selected arms as feedback. In this p…

Accelerating Primal-dual Methods for Regularized Markov Decision Processes

2022-02-21 · Haoya Li, Hsiang-Fu Yu, Lexing Ying, Inderjit Dhillon

Entropy regularized Markov decision processes have been widely used in reinforcement learning. This paper is concerned with the primal-dual formulation of the entropy regularized problems. Standard first-order methods su…

reinforcement-learningReinforcement Learning (RL)

Efficient reformulations of ReLU deep neural networks for surrogate modelling in power system optimisation

2026-01-21 · Yogesh Pipada Sunil Kumar, S. Ali Pourmousavi, Jon A. R. Liisberg, Julian Lesmos-Vinasco arxiv

The ongoing decarbonisation of power systems is driving an increasing reliance on distributed energy resources, which introduces complex and nonlinear interactions that are difficult to capture in conventional optimisati…