Training structured neural networks through manifold identification and variance reduction
ZS Huang, C Lee - arXiv preprint arXiv:2112.02612, 2021 - arxiv.org
This paper proposes an algorithm (RMDA) for training neural networks (NNs) with a
regularization term for promoting desired structures. RMDA does not incur computation …
regularization term for promoting desired structures. RMDA does not incur computation …
Newton acceleration on manifolds identified by proximal gradient methods
Proximal methods are known to identify the underlying substructure of nonsmooth
optimization problems. Even more, in many interesting situations, the output of a proximity …
optimization problems. Even more, in many interesting situations, the output of a proximity …
Precoder Design for User-Centric Network Massive MIMO with Matrix Manifold Optimization
In this paper, we investigate the precoder design for user-centric network (UCN) massive
multiple-input multiple-output (mMIMO) downlink with matrix manifold optimization. In UCN …
multiple-input multiple-output (mMIMO) downlink with matrix manifold optimization. In UCN …
A proximal-gradient method for problems with overlapping group-sparse regularization: support identification complexity
Y Dai, DP Robinson - Optimization Methods and Software, 2024 - Taylor & Francis
We consider the proximal-gradient method for minimizing the sum of a smooth function and
a convex non-smooth overlapping group-ℓ 1 regularizer, which is known to promote sparse …
a convex non-smooth overlapping group-ℓ 1 regularizer, which is known to promote sparse …
Sampling-based methods for multi-block optimization problems over transport polytopes
This paper focuses on multi-block optimization problems over transport polytopes, which
underlie various applications including strongly correlated quantum physics and machine …
underlie various applications including strongly correlated quantum physics and machine …
A Stochastic Block-coordinate Proximal Newton Method for Nonconvex Composite Minimization
H Zhu, X Qian - arXiv preprint arXiv:2412.18394, 2024 - arxiv.org
We propose a stochastic block-coordinate proximal Newton method for minimizing the sum
of a blockwise Lipschitz-continuously differentiable function and a separable nonsmooth …
of a blockwise Lipschitz-continuously differentiable function and a separable nonsmooth …
Accelerated projected gradient algorithms for sparsity constrained optimization problems
JH Alcantara, C Lee - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We consider the projected gradient algorithm for the nonconvex best subset selection
problem that minimizes a given empirical loss function under an $\ell_0 $-norm constraint …
problem that minimizes a given empirical loss function under an $\ell_0 $-norm constraint …
Sampling-Based Approaches for Multimarginal Optimal Transport Problems with Coulomb Cost
The multimarginal optimal transport problem with Coulomb cost arises in quantum physics
and is vital in understanding strongly correlated quantum systems. Its intrinsic curse of …
and is vital in understanding strongly correlated quantum systems. Its intrinsic curse of …
Inexact proximal-gradient methods with support identification
Y Dai, DP Robinson - arXiv preprint arXiv:2211.02214, 2022 - arxiv.org
We consider the proximal-gradient method for minimizing an objective function that is the
sum of a smooth function and a non-smooth convex function. A feature that distinguishes our …
sum of a smooth function and a non-smooth convex function. A feature that distinguishes our …
Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network
ZS Huang, C Lee - arXiv preprint arXiv:2403.14398, 2024 - arxiv.org
We propose a Regularized Adaptive Momentum Dual Averaging (RAMDA) algorithm for
training structured neural networks. Similar to existing regularized adaptive methods, the …
training structured neural networks. Similar to existing regularized adaptive methods, the …