Paper speeds up tensor factorization algorithms.
problem Improving convergence speed of tensor factorization algorithms.
method Proposes an extrapolation strategy between block updates.
result HER significantly accelerates convergence speed.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “block-coordinate descent”
We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points. Armed with this capability, we conduct a thorough comparison between the full kernel, the Nyström method, and random features on three large classification tasks from va…
We consider convex-concave saddle point problems with a separable structure and non-strongly convex functions. We propose an efficient stochastic block coordinate descent method using adaptive primal-dual updates, which enables flexible parallel optimization for large-scale problems. Our method shares the efficiency an…
While convergence of the Alternating Direction Method of Multipliers (ADMM) on convex problems is well studied, convergence on nonconvex problems is only partially understood. In this paper, we consider the Gaussian phase retrieval problem, formulated as a linear constrained optimization problem with a biconvex objecti…
Differentially private random block coordinate descent improves utility in machine learning.
problem Lack of privacy in classical CD methods when handling sensitive information.
method Proposes a differentially private random block coordinate descent method using sketch matrices and importance sampling.
result Demonstrates improved convergence rates and utility guarantees compared to non-private methods.
Nonnegative matrix factorization (NMF) has attracted much attention in the last decade as a dimension reduction method in many applications. Due to the explosion in the size of data, naturally the samples are collected and stored distributively in local computational nodes. Thus, there is a growing need to develop algo…
This paper introduces a new method for optimizing large-scale problems using Markov chain block updates.
problem Optimizing large-scale problems with efficient and natural block selection.
method Markov chain block coordinate descent (BCD) for optimization.
result The method converges for minimizing Lipschitz differentiable functions, with sublinear and linear convergence rates for convex and strongly convex functions, respectively.
Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of parameters of DNNs and is used along with gradient descent-type algorithms for this optim…
By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm consisting of a sequence of numerically well-behaved convex optimizations. Using…
This paper provides a block coordinate descent algorithm to solve unconstrained optimization problems. In our algorithm, computation of function values or gradients is not required. Instead, pairwise comparison of function values is used. Our algorithm consists of two steps; one is the direction estimate step and the o…
In this paper we consider the problem of minimizing a convex function using a randomized block coordinate descent method. One of the key steps at each iteration of the algorithm is determining the update to a block of variables. Existing algorithms assume that in order to compute the update, a particular subproblem is …
BCD algorithm finds global minima in neural networks.
problem Training deep neural networks to find global minima.
method Block coordinate descent with skip connections and non-negative projection.
result Proves convergence to global minima for strictly monotonic and ReLU activations.
Paper compares optimization methods for sparse NCP decomposition of tensors.
problem Efficiently extract meaningful nonnegative and sparse components from tensors.
method Sparse NCP decomposition with l1-norm regularization and block coordinate descent.
result Comparison of optimization methods for tensor decomposition effectiveness and speed.
BCD-prox improves robustness and accuracy in filtering and parameter estimation.
problem Simultaneous filtering and parameter estimation of complex ODE models.
method Block coordinate descent proximal algorithm (BCD-prox) for ODE systems.
result BCD-prox outperforms state-of-the-art methods in robustness, accuracy, and training time.
We consider a generic convex-concave saddle point problem with separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual updates for saddle point problems, and incorporate stochastic block coordinate descent with adaptive st…
Two-layer model sparsifies image residuals for CT image reconstruction.
problem Image reconstruction from limited and corrupted data.
method Pre-learning a two-layer sparsifying transform model with block coordinate descent optimization.
result Preliminary experiments show the two-layer model improves CT image reconstruction from low-dose measurements.
We establish that first-order methods avoid saddle points for almost all initializations. Our results apply to a wide variety of first-order methods, including gradient descent, block coordinate descent, mirror descent and variants thereof. The connecting thread is that such algorithms can be studied from a dynamical s…
A new method solves the projection robust Wasserstein distance problem efficiently.
problem Computing the projection robust Wasserstein distance is challenging due to the curse of dimensionality.
method Riemannian block coordinate descent (RBCD) method to solve the regularized max-min problem over the Stiefel manifold.
result RBCD method significantly improves the complexity of obtaining an ε-stationary point compared to existing methods.
Proposes a self-paced multi-label learning method to handle diverse labels efficiently.
problem Learning from multi-label data with a large label space is NP-hard and prone to overfitting.
method Self-paced multi-label learning with diversity (SPMLD) approach, incorporating gradual label inclusion and diversity maintenance.
result The proposed SPMLD framework optimizes a non-convex objective function using block coordinate descent.
Deep learning has aroused extensive attention due to its great empirical success. The efficiency of the block coordinate descent (BCD) methods has been recently demonstrated in deep neural network (DNN) training. However, theoretical studies on their convergence properties are limited due to the highly nonconvex nature…
We propose a variable decomposition algorithm -greedy block coordinate descent (GBCD)- in order to make dense Gaussian process regression practical for large scale problems. GBCD breaks a large scale optimization into a series of small sub-problems. The challenge in variable decomposition algorithms is the identificati…
In this paper we analyze the randomized block-coordinate descent (RBCD) methods proposed in [8,11] for minimizing the sum of a smooth convex function and a block-separable convex function. In particular, we extend Nesterov's technique developed in [8] for analyzing the RBCD method for minimizing a smooth convex functio…
LPOM approximates neural nets with proximal operators for efficient training.
problem Training feed-forward neural networks efficiently and avoiding gradient issues.
method Rewriting activation functions as proximal operators, using block coordinate descent.
result LPOM converges and performs well on MNIST and CIFAR-10.
In this article, we derive a Bayesian model to learning the sparse and low rank PARAFAC decomposition for the observed tensor with missing values via the elastic net, with property to find the true rank and sparse factor matrix which is robust to the noise. We formulate efficient block coordinate descent algorithm and …
In this paper we develop a randomized block-coordinate descent method for minimizing the sum of a smooth and a simple nonsmooth block-separable convex function and prove that it obtains an -accurate solution with probability at least in at most iterations, where is the numbe…
Fenchel lifted networks improve neural network training without performance loss.
problem The difficulty and non-convexity of training deep neural networks.
method Introduces Fenchel lifted networks that represent activation functions as biconvex constraints and uses Lagrange Multipliers to create a lower bound of the training problem.
result Fenchel lifted networks match or outperform traditional neural networks in performance.
We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable, but let them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making th…
Training structured prediction models is time-consuming. However, most existing approaches only use a single machine, thus, the advantage of computing power and the capacity for larger data sets of multiple machines have not been exploited. In this work, we propose an efficient algorithm for distributedly training stru…
This paper studies the partial estimation of Gaussian graphical models from high-dimensional empirical observations. We derive a convex formulation for this problem using -regularized maximum-likelihood estimation, which can be solved via a block coordinate descent algorithm. Statistical estimation performance …
Study tackles nonlinear factor models with unknown monotone links from incomplete and noisy data.
problem Learning nonlinear factor models with unknown monotone links from incomplete and noisy data.
method Formulated as joint recovery of low-rank factors, loadings, and nonlinear link function; proposed BCD algorithm with regularization.
result Established convergence guarantees and sublinear regret bounds for link-function updates.
PARC uses piecewise linear predictors for regression and classification.
problem Multivariate regression and classification problems.
method Alternates between ridge and softmax regression, and cluster assignment based on accuracy and separability.
result Converges to a local minimum in a finite number of steps.
Unified framework for coupled tensor completion improves recovery accuracy.
problem Improving recovery accuracy in coupled tensor completion.
method Unified framework using tensor ring (TR) decomposition with shared latent factors and novel optimization model.
result The proposed method achieves superior recovery accuracy on real-world data compared to state-of-the-art methods.
A novel hierarchical Bayesian approach to Federated Learning reduces data exposure and improves convergence rates.
problem Data privacy and convergence in Federated Learning.
method Hierarchical Bayesian modeling and block-coordinate descent optimization.
result The proposed algorithm converges to an optimal solution with a rate of and guarantees vanishing generalization error.
Clusterpath estimator simplifies graphical model interpretation for large datasets.
problem Difficulty in interpreting graphical models with many variables.
method Clusterpath estimator that groups variables for block-structured precision matrix.
result CGGM outperforms other methods in variable clustering and practical applications.
Paper shows how to use geometric median for robust SGD in high dimensions.
problem Robustifying SGD for high-dimensional optimization problems with gross corruption.
method Applying geometric median to only chosen blocks of coordinates at a time.
result Retains optimal breakdown point of 0.5 for smooth non-convex problems.
In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contributions. First, we provide a unified viewpoint for several first-order optimization techniques such as …
New method improves scalability of SGD for large datasets.
problem High variance in stochastic gradient descent.
method Adaptive measure reduction with Carathéodory's theorem.
result Improved scalability to high-dimensional spaces.
The cyclic block coordinate descent-type (CBCD-type) methods, which performs iterative updates for a few coordinates (a block) simultaneously throughout the procedure, have shown remarkable computational performance for solving strongly convex minimization problems. Typical applications include many popular statistical…
New method identifies latent components in PNL mixtures without strong assumptions.
problem Identifying latent components in PNL mixtures under unknown nonlinear functions.
method Carefully designed UML criterion to identify a null space associated with the mixing system.
result Identification/removal of unknown nonlinearity under minimal conditions.
Paper proposes a framework and algorithm for model compression in neural networks.
problem Training neural networks with model compression techniques suffers from accuracy loss and convergence issues.
method Holistic framework based on nonconvex optimization, using NN-BCD algorithm with closed-form iteration scheme.
result The proposed algorithm globally converges to a critical point at a rate of O(1/k).
SPAN learns functions over sets invariant to permutations, outperforming existing methods.
problem Learning functions over sets invariant to permutations.
method SPAN architecture that combines neural networks with adversarial permutations.
result SPAN achieves nearly permutation-invariant functions while maintaining accuracy.
We propose regularizing the empirical loss for semi-supervised learning by acting on both the input (data) space, and the weight (parameter) space. We show that the two are not equivalent, and in fact are complementary, one affecting the minimality of the resulting representation, the other insensitivity to nuisance va…
New Frank-Wolfe method for sparse neural networks.
problem Training sparse neural networks.
method Combines Frank-Wolfe steps and steepest descent steps, with in-face directions and block coordinate steps.
result Significant improvements in training sparse neural networks.
A note on the relations between mixture models, maximum-likelihood and entropic optimal transportstat.ML
Simplified explanation of ML for mixtures and OT.
problem Maximum likelihood estimation for mixture models.
method Optimal transport with entropic regularization.
result EM algorithm is a block-coordinate descent on OT loss.
New algorithm for nonconvex optimization on constrained Riemannian manifolds converges quickly.
problem Optimization on constrained Riemannian manifolds.
method Block majorization-minimization (BMM) for smooth nonconvex objectives with Riemannian constraints.
result Converges to stationary points within iterations.
A framework for collaborative learning reduces communication rounds.
problem Collaborative learning with distributed features and privacy concerns.
method Federated Stochastic Block Coordinate Descent (FedBCD) algorithm.
result The algorithm achieves communication rounds and accuracy.
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules. We consider rules in both conjunctive normal form (AND-of-ORs) and disjunctive normal form (OR-of-ANDs). A principled objective function is proposed to trade …
We introduce a new algorithm, called adaptive sparse backfitting algorithm, for solving high dimensional Sparse Additive Model (SpAM) utilizing symmetric, non-negative definite smoothers. Unlike the previous sparse backfitting algorithm, our method is essentially a block coordinate descent algorithm that guarantees to …