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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Convex Loss”

On the transferability of adversarial examples between convex and 01 loss modelscs.LG

The paper explores transferability of adversarial examples between convex and 01 loss models, finding non-transferability due to different decision boundaries caused by outliers.

problem Transferability of adversarial examples between convex and 01 loss models.

method Empirical study of transferability between linear 01 loss and convex (hinge) loss models, and between neural networks with different activation functions.

result Adversarial examples are non-transferable between convex and 01 loss models due to different decision boundaries caused by outliers.

adversarial examples transferability convex loss 01 loss outliers

2020-06-14abs ↗pdf ↗

The Lovász Hinge: A Novel Convex Surrogate for Submodular Lossesstat.ML

Novel convex surrogate for submodular losses with tractable computation.

problem Learning with non-modular losses for set prediction.

method Proposed Lovász hinge loss function for submodular losses.

result First tractable convex surrogates for submodular losses.

submodular losses convex surrogates Lovász hinge set prediction PASCAL VOC

2015-12-24abs ↗pdf ↗

On the connections between algorithmic regularization and penalization for convex lossesmath.OC

Equivalence found between algorithmic regularization and convex penalization for convex losses.

problem Understanding the relationship between algorithmic regularization and convex penalization.

method Introducing a geometric condition and showing equivalence through optimization paths.

result Optimization paths of iterative algorithms on unregularized problems match those of corresponding penalized problems under certain conditions.

algorithmic regularization convex penalization convex losses optimization paths geometric condition

2019-09-08abs ↗pdf ↗

Minimizing The Misclassification Error Rate Using a Surrogate Convex Losscs.LG

We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…

2012-06-27abs ↗pdf ↗

A Convex Surrogate Operator for General Non-Modular Loss Functionsstat.ML

Novel convex surrogate for non-modular loss functions.

problem Computational tractability for non-modular loss functions.

method Submodular-supermodular decomposition, slack-rescaling, Lov{á}sz hinge.

result First tractable solution for non-modular loss functions.

convex surrogates non-modular loss submodular-supermodular decomposition empirical risk minimization optimization

2016-04-12abs ↗pdf ↗

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Lossescs.LG

We establish linear regret bounds for convex smooth losses using Fenchel-Young losses.

problem Establishing linear regret bounds for convex smooth losses.

method Constructing a convex smooth surrogate loss using Fenchel-Young losses generated by the convolutional negentropy.

result We derive a smooth loss with a linear surrogate regret bound.

surrogate regret bounds convex smooth losses Fenchel-Young losses convolutional negentropy linear regret bound

2025-05-14abs ↗pdf ↗

Fast Global Convergence via Landscape of Empirical Lossstat.ML

Paper shows non-convex loss functions can be optimized efficiently.

problem Optimizing non-convex loss functions is challenging.

method Uses stochastic variance reduction methods to find global optimal solutions.

result Stochastic variance reduction methods converge to global optimal with linear rate.

non-convex optimization stochastic variance reduction global convergence empirical loss machine learning

2018-02-13abs ↗pdf ↗

A Note On Nonlinear Regression Under L2 Losscs.LG

We find a convex model for traditional nonlinear regression under L2 loss.

problem Nonlinear regression under L2 loss with non-convex optimization.

method Showed a convex nonlinear regression model for least squares problem.

result Existence of a convex model simplifies training complex systems.

nonlinear regression convex optimization least squares L2 loss

2023-03-30abs ↗pdf ↗

Learning with Non-Convex Truncated Losses by SGDcs.LG

Paper studies non-convex truncated loss functions for robust learning.

problem Improving generalization with non-convex loss functions.

method Truncating traditional loss functions and using SGD.

result Excess risk bounds and stationary points found by SGD.

non-convex loss truncated loss stochastic gradient descent generalization robust learning

2018-05-21abs ↗pdf ↗

Structured Prediction with Projection Oraclesstat.ML

The paper proposes a framework for structured prediction using projection oracles.

problem Structured prediction with improved loss functions.

method A general framework for deriving loss functions using convex sets and projection oracles.

result Projections onto the marginal polytope can make the loss smaller and are computationally efficient.

structured prediction projection oracle convex sets loss functions label ranking

2019-10-24abs ↗pdf ↗

Convex Calibration Dimension for Multiclass Loss Matricescs.LG

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning pro…

2014-08-12abs ↗pdf ↗

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedbackcs.LG

Improved online learning for hidden-convex losses achieves optimal regret.

problem Adversarial online learning with nonconvex losses that become convex after reparameterization.

method Algorithmic equivalence between OGD and OMD on convex losses, with Hessian compatibility condition.

result OGD achieves

\mathcal{O}(\sqrt{T})

regret for hidden-convex losses, matching optimal rate.

online learning hidden-convex losses algorithmic equivalence regret minimization Hessian compatibility

2026-05-25abs ↗pdf ↗

Making Convex Loss Functions Robust to Outliers using

e

-Exponentiated Transformationcs.LG

Paper proposes a new $e$ -exponentiated transformation to make convex loss functions more robust to outliers.

problem Making convex loss functions robust to outliers in the presence of label noise.

method Introduces a novel

e

-exponentiated transformation for loss functions and proves its effectiveness through theoretical and empirical analysis.

result The transformed loss function achieves tighter generalization error bounds and higher accuracy in noisy datasets.

outliers convex loss functions generalization error label noise empirical validation

2019-02-16abs ↗pdf ↗

Consistent Robust Adversarial Prediction for General Multiclass Classificationstat.ML

Proposes a robust framework for multiclass classification.

problem General multiclass classification with adversarial robustness.

method Dual formulation as convex optimization with adversarial surrogate loss.

result Competitive performance in multiclass classification problems.

multiclass classification adversarial robustness surrogate loss convex optimization kernel trick

2018-12-18abs ↗pdf ↗

Composite Binary Lossesstat.ML

We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise when margin losses can be proper composite losses, explicitly show how to determ…

2009-12-17abs ↗pdf ↗

On Structured Prediction Theory with Calibrated Convex Surrogate Lossescs.LG

The study offers new theoretical insights into structured prediction with convex loss minimization.

problem The challenge of structured prediction with efficient convex surrogate loss minimization.

method Constructing a convex surrogate loss and proving tight bounds on the calibration function.

result Formalizes the intuition that some task losses make learning harder than others, and that 0-1 loss is ill-suited for general structured prediction.

structured prediction calibrated convex surrogate consistency guarantees stochastic gradient descent exponential number of classes

2017-03-07abs ↗pdf ↗

Private Stochastic Convex Optimization with Optimal Ratescs.LG

Private algorithms minimize population loss with optimal rate.

problem Private optimization of convex functions with stochastic samples.

method Differentially private algorithms based on algorithmic stability.

result Optimal rate of

1/\sqrt{n}

for population loss.

private optimization stochastic convex optimization differential privacy algorithmic stability convex functions

2019-08-27abs ↗pdf ↗

The Geometry and Calculus of Lossescs.LG

Develops a new theory of loss functions for statistical machine learning.

problem Evaluation of solutions in binary and multiclass classification problems.

method Defines loss functions as subgradients of support functions of convex sets, enabling a calculus of losses.

result Provides a novel perspective on losses and develops a calculus that interpolates between different losses.

loss functions convex sets subgradient support function calculus of losses

2022-09-01abs ↗pdf ↗

The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex losscs.LG

Unhinged loss minimization fails to improve classifier accuracy for simple data.

problem Accuracy of classifiers minimizing the unhinged loss.

method Minimizing the unhinged loss function.

result Minimizing the unhinged loss yields classifiers with accuracy no better than random guessing for simple data.

unhinged loss classifier accuracy random guessing convex loss binary classification

2021-12-08abs ↗pdf ↗

Stability of SGD: Tightness Analysis and Improved Boundscs.LG

Paper improves stability analysis of SGD for various loss functions and data distributions.

problem Improving stability analysis of SGD for non-convex loss functions and data distributions.

method Analyzes stability of SGD for convex and non-convex loss functions, and improves data-dependent bounds.

result Improved stability bounds for non-convex loss functions and convex regularized loss functions.

Stochastic Gradient Descent Generalization Loss Functions Data Distribution Convex Optimization

2021-02-10abs ↗pdf ↗

Calibrated Surrogate Losses for Adversarially Robust Classificationstat.ML

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.

Adversarial robustness Calibration Surrogate losses Convex optimization Nonconvex optimization

2020-05-28abs ↗pdf ↗

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Datacs.LG

Improved privacy-preserving methods for convex optimization with heavy-tailed data.

problem Privacy-preserving optimization of convex functions with heavy-tailed data.

method Developed algorithms for private mean estimation and convex optimization under concentrated differential privacy constraints.

result Achieved improved upper bounds on excess population risk for convex and strongly convex loss functions.

differential privacy stochastic optimization convex optimization heavy-tailed data mean estimation

2021-06-02abs ↗pdf ↗

Boosting in the presence of outliers: adaptive classification with non-convex loss functionsstat.ML

This paper examines the role and efficiency of the non-convex loss functions for binary classification problems. In particular, we investigate how to design a simple and effective boosting algorithm that is robust to the outliers in the data. The analysis of the role of a particular non-convex loss for prediction accur…

2015-10-05abs ↗pdf ↗

Exploring Local Norms in Exp-concave Statistical Learningcs.LG

Optimizes exp-concave losses with a new risk bound.

problem Optimizing exp-concave losses with stochastic convex optimization.

method Empirical Risk Minimization with a unified geometric assumption and local norms.

result Provides an

O( d / n + \log( 1 / δ) / n )

excess risk bound.

stochastic convex optimization exp-concave losses Empirical Risk Minimization local norms geometric assumption

2023-02-21abs ↗pdf ↗

Faster Differentially Private Convex Optimization via Second-Order Methodscs.LG

Second-order methods improve differential privacy in convex optimization.

problem Improving differential privacy in convex optimization.

method Developed a private variant of the regularized cubic Newton method for strongly convex loss functions.

result Achieves quadratic convergence and optimal excess loss for strongly convex loss functions.

differential privacy convex optimization second-order methods Newton's method excess loss

2023-05-22abs ↗pdf ↗

Misclassification excess risk bounds for PAC-Bayesian classification via convexified lossstat.ML

This research improves PAC-Bayesian bounds for classification tasks using convexified loss.

problem Deriving generalization bounds for classification tasks with non-convex loss functions.

method Shift focus to misclassification excess risk bounds for PAC-Bayesian classification using convex surrogate loss and leveraging PAC-Bayesian relative bounds in expectation.

result Improved PAC-Bayesian bounds for classification tasks with convex surrogate loss.

PAC-Bayesian classification convexified loss misclassification excess risk

2024-08-16abs ↗pdf ↗

On Symmetric Losses for Learning from Corrupted Labelsstat.ML

The paper explores symmetric losses for better learning from corrupted labels.

problem Learning from corrupted labels with balanced error rate or AUC maximization.

method Proves theoretical properties of symmetric losses and proposes a convex barrier hinge loss.

result Symmetric losses are advantageous in BER minimization and AUC maximization from corrupted labels.

symmetric loss corrupted labels balanced error rate AUC convex barrier hinge loss

2019-01-27abs ↗pdf ↗

Distributed Online Non-convex Optimization with Composite Regretcs.LG

New approach for distributed online optimization of non-convex losses with sublinear regret.

problem Regret evaluation and consensus in distributed, multi-agent systems with non-convex losses.

method Composite regret metric and consensus-based online normalized gradient (CONGD) approach for pseudo-convex losses; offline optimization oracle for general non-convex losses.

result First sublinear regret bound for general distributed online non-convex learning.

distributed optimization non-convex losses composite regret consensus sublinear regret

2022-09-21abs ↗pdf ↗

Bias-Variance Decompositions for Margin Lossesstat.ML

We analyze bias-variance of margin losses.

problem Understanding model overfitting/underfitting.

method Bias-variance decomposition for strictly convex margin losses.

result Expected risk decomposes into central model risk and data variation.

bias-variance margin losses convex optimization logitboost ensemble models

2022-04-26abs ↗pdf ↗

Generalized XGBoost Methodcs.LG

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.

XGBoost loss function nonconvex multivariate parameter estimation

2021-09-15abs ↗pdf ↗

Improved Guarantees for Constrained Online Convex Optimization via Self-Contractioncs.LG

Improved COCO algorithms with better constraint control.

problem Achieving small regret and constraint violation in online convex optimization.

method Simple projection-based algorithm leveraging self-contraction geometry.

result Exponential improvement in cumulative constraint violation for strongly convex losses.

Online Convex Optimization Constrained Optimization Self-Contraction Regret Minimization Constraint Violation

2026-05-20abs ↗pdf ↗

Two-temperature logistic regression based on the Tsallis divergencecs.LG

A robust multiclass logistic regression method using Tsallis divergence.

problem Noise robustness in multiclass logistic regression.

method Two-temperature logistic regression with Tsallis divergence.

result Significant robustness to outliers and noise.

logistic regression Tsallis divergence robustness multiclass non-convex

2017-05-19abs ↗pdf ↗

DC Proximal Newton for Non-Convex Optimization Problemscs.LG

We introduce a novel algorithm for solving learning problems where both the loss function and the regularizer are non-convex but belong to the class of difference of convex (DC) functions. Our contribution is a new general purpose proximal Newton algorithm that is able to deal with such a situation. The algorithm consi…

2015-07-02abs ↗pdf ↗

The Nyström method for convex loss functionsstat.ML

The Nyström method improves learning efficiency for convex losses.

problem Improving computational efficiency in empirical risk minimization.

method Using random subspaces to approximate hypothesis spaces in convex loss functions.

result Computational gains can be achieved without sacrificing learning performance for general convex Lipschitz losses.

Nyström method convex loss empirical risk minimization random subspaces classification error bounds

2020-06-17abs ↗pdf ↗

Projection-free Distributed Online Learning with Sublinear Communication Complexitycs.LG

Improved algorithm reduces communication rounds for distributed online learning.

problem Complicated constraints in distributed online learning with locally light computations.

method Proposed D-BOCG algorithm with delayed update mechanism and redefined surrogate loss function.

result Achieved

O(T^{3/4})

regret bound with

O(\sqrt{T})

communication rounds for convex losses.

distributed online learning projection-free delayed update surrogate loss regret bound

2021-03-20abs ↗pdf ↗

Stability of Stochastic Gradient Descent on Nonsmooth Convex Lossescs.LG

New stability bounds for SGD on nonsmooth convex losses.

problem Understanding stability of SGD on nonsmooth convex losses.

method Sharp upper and lower bounds for SGD and full-batch GD on nonsmooth convex losses.

result SGD can be less stable but still useful for generalization bounds.

stability SGD convex optimization nonsmooth uniform stability

2020-06-12abs ↗pdf ↗

Online Convex Optimization with Unconstrained Domains and Lossescs.LG

Optimal online optimization algorithm without loss bounds.

problem Online convex optimization in unconstrained domains and losses.

method RescaledExp algorithm achieving optimal regret.

result RescaledExp matches lower bound asymptotically.

online optimization convex optimization unconstrained domains loss functions regret minimization

2017-03-07abs ↗pdf ↗

A Convex Loss Function for Set Prediction with Optimal Trade-offs Between Size and Conditional Coveragecs.LG

A new convex loss function optimizes set predictions with balanced size and coverage.

problem Optimizing set predictions with balanced size and coverage.

method Proposes a convex loss function using Choquet integrals for nondecreasing subset-valued functions.

result Optimal trade-offs between conditional probabilistic coverage and set size.

set prediction convex loss function Choquet integrals submodular function binary classification

2025-12-22abs ↗pdf ↗

Deep linear neural networks with arbitrary loss: All local minima are globalcs.LG

Deep linear networks with arbitrary loss have all local minima as global minima.

problem Finding optimal solutions in deep linear networks with arbitrary convex losses.

method Provided a short and elementary proof for all local minima being global minima under specific conditions.

result All local minima are global minima for deep linear networks with certain layer widths.

deep linear networks local minima global minima convex loss layer width

2017-12-05abs ↗pdf ↗

Small Gradient Norm Regret for Online Convex Optimizationstat.ML

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

problem Online convex optimization with smooth losses.

method Introduces a new

G^\star

regret measure that depends on the cumulative squared gradient norm.

result The

G^\star

regret can be arbitrarily sharper than existing measures when losses have vanishing curvature.

online convex optimization regret smooth losses gradient norm vanishing curvature

2026-01-20abs ↗pdf ↗

Learning Multi-Attribute Differential Graphs with Non-Convex Penaltiesstat.ML

Paper estimates differences in multi-attribute Gaussian graphical models using non-convex penalties.

problem Estimating differences in multi-attribute Gaussian graphical models with similar structure.

method Penalized D-trace loss function with non-convex (log-sum and SCAD) penalties, proximal gradient descent methods.

result Theoretical analysis and numerical examples support consistency in support recovery and estimation.

graphical models penalized loss non-convex penalties differential graph estimation Gaussian graphical models

2025-05-14abs ↗pdf ↗

The Convexity and Design of Composite Multiclass Lossescs.LG

We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using …

2012-06-18abs ↗pdf ↗

Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcs.LG

Paper improves privacy in ERM with faster algorithms and broader applicability.

problem Privacy-preserving machine learning with empirical risk minimization.

method Develops faster algorithms for differentially private ERM in various settings.

result Achieves optimal or near-optimal utility bounds with less gradient complexity.

differential privacy empirical risk minimization gradient complexity smooth convex loss high-dimensional setting

2018-02-14abs ↗pdf ↗

Optimal convex

M

-estimation via score matchingmath.ST

Optimal convex loss function improves regression coefficient estimation.

problem Asymptotic variance improvement in linear regression estimation.

method Score matching extension for log-concave projection.

result Semiparametric estimator attains minimal asymptotic covariance.

linear regression convex loss score matching asymptotic efficiency log-concave projection

2024-03-25abs ↗pdf ↗

Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Lossesmath.OC

In this work we develop a new algorithm for regularized empirical risk minimization. Our method extends recent techniques of Shalev-Shwartz [02/2015], which enable a dual-free analysis of SDCA, to arbitrary mini-batching schemes. Moreover, our method is able to better utilize the information in the data defining the ER…

2015-06-07abs ↗pdf ↗

Optimal Binary Classifier Aggregation for General Lossescs.LG

We address the problem of aggregating an ensemble of predictors with known loss bounds in a semi-supervised binary classification setting, to minimize prediction loss incurred on the unlabeled data. We find the minimax optimal predictions for a very general class of loss functions including all convex and many non-conv…

2015-10-01abs ↗pdf ↗

Logitron: Perceptron-augmented classification model based on an extended logistic loss functioncs.LG

Logitron combines Perceptron and logistic loss for improved classification.

problem Non-convex and non-smooth zero-one loss function in classification models.

method Introduces a Perceptron-augmented convex classification framework with an extended logistic loss function.

result Hinge-Logitron outperforms logistic regression and SVM in classification accuracy.

classification logistic regression Perceptron logistic loss Hinge loss

2019-04-05abs ↗pdf ↗

Revisiting Projection-Free Online Learning with Time-Varying Constraintscs.LG

Improved online learning with time-varying constraints for complex domains.

problem Constrained online convex optimization with time-varying constraints.

method Constructing a composite surrogate loss and using the online Frank-Wolfe method.

result Novel regret and cumulative constraint violation bounds for strongly convex losses.

online learning constrained optimization time-varying constraints composite surrogate loss Frank-Wolfe method

2025-01-27abs ↗pdf ↗