Research
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

53106159212 · Jun 202019922001200920182026
48 results for convex surrogates

The study develops a theory for structured prediction using smooth convex surrogates.

problem Developing a theoretical framework for structured prediction.
method Characterizing smooth convex surrogates compatible with task losses and deriving statistical guarantees.
result Derives tight bounds for the calibration function and novel results for existing surrogate frameworks.

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.

New framework quantifies learning guarantees for inconsistent convex surrogates.

problem Analyzing consistency properties of machine learning methods with inconsistent convex surrogates.
method Extending the framework of Osokin et al. (2017) to inconsistent surrogates, introducing a new lower bound on the calibration function.
result Shows how learning with inconsistent surrogates can have guarantees on sample complexity and optimization difficulty.

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.

Paper extends SMM to weakly convex and multi-convex surrogates for non-convex optimization.

problem Non-convex optimization with weakly convex or multi-convex surrogates.
method Stochastic majorization-minimization with proximal regularization or block-minimization.
result Convergence rates for empirical and expected losses under non-i.i.d. data.

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 ↗

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 consistency depends on the uniqueness of adversarial Bayes classifiers.

problem Consistency of adversarial surrogate losses is not guaranteed.
method Connected consistency of adversarial surrogate losses to the uniqueness of adversarial Bayes classifiers.
result A convex surrogate loss is statistically consistent for adversarial learning if and only if the adversarial Bayes classifier is unique.

Paper proposes equivalent Lipschitz surrogates for zero-norm and rank optimization problems.

problem Optimization problems involving zero-norm and rank functions.
method Reformulate as MPECs, use global exact penalty, eliminate dual variable to get surrogates.
result Obtained equivalent Lipschitz surrogates for zero-norm and rank optimization problems.

The paper explores trading off consistency and dimensionality in convex surrogates for multiclass classification.

problem Designing consistent surrogate losses for multiclass classification with high-dimensional outcomes.
method Investigates embedding outcomes into convex polytopes and examining consistency under low-noise assumptions.
result Consistency can be achieved with less than n1n-1 dimensions, but hallucination occurs for some distributions.

We develop a framework for consistent polyhedral surrogates in classification and prediction.

problem Designing consistent polyhedral surrogates for classification and prediction problems.
method Formalizing and studying embeddings of predictions as points in R^d, assigning original loss values, and convexifying to create surrogates.
result Established a strong connection between embeddings and polyhedral surrogates, providing constructions and proofs of consistency or inconsistency.

Optimizes hard-to-optimize metrics using adaptive surrogates.

problem Training models with black-box and hard-to-optimize metrics.
method Expresses metric as a function of surrogates, solves optimization problem over relaxed surrogate space.
result Approach performs on par with known methods and adds value when metric form is unknown.

New method simplifies checking consistency of differentiable loss functions.

problem Verifying consistency of differentiable loss functions is difficult.
method Developed a new approach called strong indirect elicitation (strong IE) to simplify checking consistency.
result Strong IE is equivalent to calibration for strongly convex, differentiable surrogates.

In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed by the fact that the smoothness is further beneficial both computationally- by at…

2014-02-07abs ↗pdf ↗

Safe reinforcement learning with nonconvex constraints using convex approximations.

problem Safe reinforcement learning with nonlinear function approximation.
method Constructing surrogate convex constrained optimization problems by replacing nonconvex functions with convex quadratic functions.
result Solutions to surrogate problems converge to a stationary point of the original nonconvex problem.

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.

New algorithm learns optimal stepsizes for SGD in noisy non-convex optimization.

problem Finding optimal stepsize for SGD in noisy non-convex optimization.
method Surrogate losses cast problem into online convex optimization, using no-regret algorithms.
result Self-tuned SGD algorithm with adaptive convergence rates.

Develops algorithms to optimize a partial area under the ROC curve.

problem Optimizing performance measures between specific false positive rates.
method Support vector algorithms based on minimizing convex surrogates for partial AUC.
result Polynomial time algorithm for solving combinatorial optimization problem associated with partial AUC.

FNNC framework ensures fairness in neural networks through convex surrogates.

problem Ensuring fairness in neural network classification models.
method FNNC framework uses neural networks to include fairness constraints in the loss function and optimizes using mini-batch stochastic gradient descent.
result FNNC achieves fairness while maintaining high accuracy, as shown by experiments.

Study on calibration and consistency of adversarial surrogate losses.

problem Designing robust classifiers with theoretical guarantees.
method Extensive analysis of H-calibration and H-consistency of adversarial surrogate losses.
result Some convex loss functions and supremum-based convex losses are not H-calibrated for important hypothesis sets.

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 ↗

New active learning framework for multiclass classification beyond realizability assumption.

problem Active learning in non-realizable settings with convex model classes.
method Surrogate risk minimization, epoch-based fitting, aggregation of models.
result Achieves label and sample complexity comparable to prior work in non-realizable settings.

Semi-supervised learning can't improve with certain loss functions.

problem Limiting improvement in semi-supervised learning with specific loss functions.
method Analysis of convex margin-based losses that are either decreasing or increasing.
result Safe improvements possible with increasing margin-based losses.

We suggest using the max-norm as a convex surrogate constraint for clustering. We show how this yields a better exact cluster recovery guarantee than previously suggested nuclear-norm relaxation, and study the effectiveness of our method, and other related convex relaxations, compared to other clustering approaches.

2012-02-25abs ↗pdf ↗

Dual explanation method using convex hulls and example-based vectors.

problem Local and global explanation of complex models.
method Dual representation of instances as convex combinations, generating new dual dataset, training linear surrogate model, computing feature importance.
result Effective example-based and local/global explanation of complex models.

Optimal bounds on regret and constraint violation in adversarial COCO.

problem Minimizing regret and cumulative constraint violation in adversarial COCO.
method New surrogate loss function and Follow-the-Regularized-Leader/Online Gradient Descent.
result Achieved optimal O(T)O(\sqrt{T}) bounds on both regret and cumulative constraint violation.

We learn a compact surrogate model for optimization problems to reduce training and inference time.

problem Solving optimization problems with unknown parameters is computationally expensive and may lead to suboptimal solutions.
method We represent the optimization problem in terms of meta-variables and learn a low-dimensional surrogate model end-to-end with the predictive model.
result We achieve a large reduction in training and inference time, and improved performance.

New approach estimates personalized treatment effects using surrogate losses.

problem Estimating personalized treatment effects with binary outcomes and limited data.
method Proposes surrogate loss functions that incorporate both treatment and control data.
result Minimax support vector machine formulation yields tighter bounds.

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.

New research shows existing information-theoretic methods can't establish minimax rates for gradient descent in stochastic convex optimization.

problem Establishing minimax rates for gradient descent in stochastic convex optimization using information-theoretic methods.
method Examined several information-theoretic frameworks including input-output mutual information bounds, conditional mutual information bounds, PAC-Bayes bounds, and their variants.
result Proved that none of the examined information-theoretic frameworks can establish minimax rates for gradient descent in stochastic convex optimization.

New method improves signal estimation by convexifying 0\ell_0-norm constraints.

problem Signal estimation with sparsity and smoothness priors.
method Iterative convex conic quadratic relaxations exploiting 0\ell_0-norm and smoothness terms.
result Significantly better estimators than 1\ell_1-norm approaches and interpretable parameters.

We consider the problem of rank loss minimization in the setting of multilabel classification, which is usually tackled by means of convex surrogate losses defined on pairs of labels. Very recently, this approach was put into question by a negative result showing that commonly used pairwise surrogate losses, such as ex…

2012-06-27abs ↗pdf ↗

AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all …

2012-08-03abs ↗pdf ↗