In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general noncon…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “nonconvex loss functions”
Proposes a generalized XGBoost method for nonconvex loss functions.
problem Limited to convex loss functions in XGBoost.
method Extends XGBoost to use nonconvex loss functions and multivariate loss functions.
result Generalized XGBoost method can model multiple parameters in various distributions.
The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperformed convex ones. However, the resultant optimization problem is much harder. In this paper, for a …
The success of deep learning has led to a rising interest in the generalization property of the stochastic gradient descent (SGD) method, and stability is one popular approach to study it. Existing works based on stability have studied nonconvex loss functions, but only considered the generalization error of the SGD in…
Develops a new framework for robust regression with EGM.
problem Addressing robust regression with heavy-tailed noise or outliers.
method Empirical gain maximization (EGM) to approximate noise density.
result Unified analysis of robust regression approaches.
MM for Penalized Estimationstat.CO
Penalized estimation can conduct variable selection and parameter estimation simultaneously. The general framework is to minimize a loss function subject to a penalty designed to generate sparse variable selection. The majorization-minimization (MM) algorithm is a computational scheme for stability and simplicity, and …
We demonstrate that the primal-dual witness proof method may be used to establish variable selection consistency and -bounds for sparse regression problems, even when the loss function and/or regularizer are nonconvex. Using this method, we derive two theorems concerning support recovery and -…
Paper proposes robust tensor regression method for tensor data analysis.
problem Outliers in tensor data analysis can make existing methods sensitive.
method Nonconvex relaxation of tensor tubal rank in optimization framework.
result Global convergence of proposed estimation algorithm under mild assumptions.
We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss surface is still incomplete. For deep linear networks, we present necessary and s…
In this paper, the estimation problem for sparse reduced rank regression (SRRR) model is considered. The SRRR model is widely used for dimension reduction and variable selection with applications in signal processing, econometrics, etc. The problem is formulated to minimize the least squares loss with a sparsity-induci…
Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optimamath.ST
We provide novel theoretical results regarding local optima of regularized -estimators, allowing for nonconvexity in both loss and penalty functions. Under restricted strong convexity on the loss and suitable regularity conditions on the penalty, we prove that \emph{any stationary point} of the composite objective f…
New robust loss functions improve matrix completion accuracy.
problem Outliers in data corrupting matrix completion accuracy.
method Developed nonconvex M-estimator functions to down-weight outliers.
result Proposed methods outperform competitors in recovery accuracy and runtime.
While many solutions for privacy-preserving convex empirical risk minimization (ERM) have been developed, privacy-preserving nonconvex ERM remains a challenge. We study nonconvex ERM, which takes the form of minimizing a finite-sum of nonconvex loss functions over a training set. We propose a new differentially private…
Proposes a new loss function for robust learning.
problem Creating a robust loss function for machine learning.
method Extended pseudo Huber loss with log-exp transform and logistic function.
result Linear convergence algorithm for minimizer finding.
With the large rising of complex data, the nonconvex models such as nonconvex loss function and nonconvex regularizer are widely used in machine learning and pattern recognition. In this paper, we propose a class of mini-batch stochastic ADMMs (alternating direction method of multipliers) for solving large-scale noncon…
New research shows many batch selection methods for training work just as well as full batch training.
problem Finding optimal batch selection methods for training.
method Analysis of mini-batch Gradient Descent (GD) and Stochastic GD (SGD) with various batch selection rules.
result All mini-batch schedules, including deterministic ones, generalize optimally for smooth Lipschitz-convex/nonconvex/strongly-convex loss functions.
Sign information is the key to overcoming the inevitable saturation error in compressive sensing systems, which causes information loss and results in bias. For sparse signal recovery from saturation, we propose to use a linear loss to improve the effectiveness from existing methods that utilize hard constraints/hinge …
Apollo improves nonconvex stochastic optimization efficiency.
problem Nonconvex stochastic optimization challenges.
method Adaptive parameter-wise diagonal quasi-Newton method approximating Hessian.
result Significant improvements in convergence speed and generalization over SGD and Adam.
New solver for MKL-SVM with 0/1 loss function.
problem Optimizing MKL-SVM with -loss function.
method Developed an ADMM solver for nonconvex, nonsmooth optimization.
result Shows promise in simple numerical experiment.
Accelerated gradient method tackles nonconvex penalties in sparse learning.
problem Optimizing nonconvex penalties in sparse statistical learning.
method Generalized Nesterov's accelerated gradient method with hyperparameter optimization.
result Convergence can be made considerably faster with optimal hyperparameters.
SGD-trained deep nets have bounds on their generalization error.
problem Bounding generalization error for deep neural networks trained by SGD.
method Combining dynamical control of parameter norms and Rademacher complexity estimates.
result Explicit bounds depend on loss trajectory, work for various architectures.
This research analyzes the consistency of convex and nonconvex surrogate losses for adversarially robust classification.
problem Ensuring classifiers are robust to adversarial perturbations.
method Analysis of convex and nonconvex surrogate losses through the lens of calibration.
result No convex surrogate loss is calibrated with respect to the adversarial 0-1 loss for linear models, but nonconvex losses can be calibrated under certain conditions.
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landscape of deep networks through the eigendecompositions of their Hessian matrix. In particular, we examine how important the negative eigenvalu…
Covariates-Adjusted Mixed-Membership Estimation: A Novel Network Model with Optimal Guaranteesmath.ST
Novel network model estimates mixed-membership structure with covariate information.
problem Estimating latent mixed-membership structure in networks with covariate information.
method Proposes a novel network model that incorporates both community information and node covariate similarities.
result Achieves optimal estimation accuracy for similarity matrix and mixed-membership.
We study theoretical properties of regularized robust M-estimators, applicable when data are drawn from a sparse high-dimensional linear model and contaminated by heavy-tailed distributions and/or outliers in the additive errors and covariates. We first establish a form of local statistical consistency for the penalize…
Unified SVM algorithm for various losses with fast training.
problem Training SVM models with different convex or nonconvex losses.
method Introducing LS-DC loss, proposing DCA-based UniSVM algorithm.
result Unified algorithm solves SVM models with any convex or nonconvex LS-DC loss efficiently.
Large learning rates lead to various implicit biases in nonconvex optimization.
problem Understanding the conditions under which large learning rates yield edge of stability, balancing, and catapult phenomena.
method Developed a global convergence theory for nonconvex functions without globally Lipschitz continuous gradient, focusing on functions with good regularity.
result These implicit biases are more likely to occur in functions with good regularity, and large learning rates favor flatter regions.
New algorithm converges to equilibrium in nonconvex-nonconcave optimization problems without dimension dependence.
problem Min-max optimization in nonconvex-nonconcave landscapes.
method Convergent algorithm with greedy max-player updates and proposal distribution for min-player.
result Algorithm converges to equilibrium in non-dependent iterations, suitable for GAN training.
This work proposes the Bregman-Tweedie classification model and analyzes the domain structure of the extended exponential function, an extension of the classic generalized exponential function with additional scaling parameter, and related high-level mathematical structures, such as the Bregman-Tweedie loss function an…
Improved complexity for smooth nonconvex optimization using quasi-Newton methods.
problem Finding ε-first-order stationary points of smooth functions with gradient information only.
method Two-level online learning approach involving quasi-Newton methods.
result Gradient complexity improved to O(d^(1/4)ε^(-13/8)) for d = O(ε^(-1/2)).
Schedule-free SGD is optimal for nonconvex optimization problems.
problem Nonconvex optimization in neural networks.
method Developed a general framework for online-to-nonconvex conversion, which converts schedule-free SGD into an effective nonconvex optimization algorithm.
result Schedule-free SGD achieves optimal iteration complexity for nonsmooth, nonconvex optimization problems.
Establishes a condition for multiclass classification-calibration of Gamma-Phi losses.
problem Ensuring classification-calibration of multiclass Gamma-Phi losses.
method Develops a general sufficient condition for classification-calibration of Gamma-Phi losses.
result Proves the first family of nonconvex multiclass surrogate losses for which classification-calibration has been fully justified.
We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from to - in particular, nonconvex, with discrete global minima. In this paper, we prove that in at least one impo…
Unified framework for constructing nonconvex sparse recovery methods.
problem Constructing valid nonconvex regularization functions remains open.
method Unified framework based on probability density function, using Weibull distribution.
result New nonconvex sparse recovery method based on Weibull distribution.
A new method speeds up deep neural network training.
problem Nonconvex optimization in deep neural networks.
method Scaled conjugate gradient method for nonconvex optimization.
result The method converges faster and achieves lower scores in practical applications.
The paper optimizes bridge-type estimators for sparse models using pathwise methods.
problem Sparse parametric models with adaptive coefficients and multiple penalties.
method Pathwise optimization with accelerated proximal gradient descent and blockwise alternating optimization.
result Efficient computation of the full solution path for adaptive bridge estimators.
This paper studies noisy low-rank matrix completion: given partial and noisy entries of a large low-rank matrix, the goal is to estimate the underlying matrix faithfully and efficiently. Arguably one of the most popular paradigms to tackle this problem is convex relaxation, which achieves remarkable efficacy in practic…
Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast number of high error saddle points present in the loss function. Second order methods have been tremendously successful and widely adopted in the…
We analyze the performance of alternating minimization for loss functions optimized over two variables, where each variable may be restricted to lie in some potentially nonconvex constraint set. This type of setting arises naturally in high-dimensional statistics and signal processing, where the variables often reflect…
New analysis for black-box learning without gradients, improving generalization bounds.
problem Generalization error analysis for derivative-free optimization.
method Zeroth-order Stochastic Search (ZoSS) algorithm for Lipschitz and smooth losses.
result Generalization bounds independent of model dimension, batch size, and number of perturbed evaluations.
New privacy bounds for DP-SGD's last iterate, even with cyclic sampling.
problem Privacy of the last iterate in DP-SGD with cyclic sampling.
method Established new RDP upper bounds for the last iterate under realistic assumptions.
result Privacy bounds for DP-SGD's last iterate with cyclic sampling and clipping, even for nonconvex losses.
Full-batch GD achieves generalization close to any stationary point with fewer assumptions.
problem Generalization and excess risk bounds for smooth losses, including non-Lipschitz and nonconvex cases.
method Path-dependent analysis of GD's generalization error, focusing on optimization error and stability.
result Generalization error is tightly bound in terms of optimization error and iteration count, bypassing common assumptions.
Adaptive SGD with Line-Search and Polyak Stepsizes: Nonconvex Convergence and Accelerated Ratesmath.OC
Improved SGD methods converge faster for nonconvex optimization.
problem Nonconvex optimization challenges in machine learning.
method Adaptive SGD with line-search and Polyak stepsizes.
result Unified convergence rates for various nonconvex functions.
As surrogate functions of -norm, many nonconvex penalty functions have been proposed to enhance the sparse vector recovery. It is easy to extend these nonconvex penalty functions on singular values of a matrix to enhance low-rank matrix recovery. However, different from convex optimization, solving the nonconvex l…
MKL--SVMstat.ML
Paper introduces MKL--SVM for SVM with loss.
problem Optimization of SVM with loss function.
method MKL framework combined with ADMM algorithm for solving the optimization problem.
result Performance of MKL--SVM comparable to SimpleMKL.
Paper proposes a new method for training nonconvex models.
problem Training nonconvex models like neural networks.
method Successive functional gradient optimization using mirror descent in a function space.
result The method leads to better performance than standard training techniques.
New framework guarantees convergence of multi-step MAML.
problem Convergence of multi-step MAML in nonconvex settings.
method Developed a theoretical framework for two types of MAML objective functions.
result Guaranteed convergence rate and computational complexity for multi-step MAML.
In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for these problems. Our key idea for making the proposed PMM to be efficient is to develop a sparse semismooth Newton method to solve the corresponding subproblem…