A new loss function improves classification accuracy in imbalanced datasets.
problem Suboptimal decision boundaries in classification with average, maximal, and average top-k losses. method Proposes a new classification objective called the close-k aggregate loss, which minimizes the loss for points close to the decision boundary. result Close-k aggregate loss achieves significant gains in 0-1 test accuracy compared to average, maximal, and average top-k losses. In this paper we study a class of insurance products where the policy holder has the option to insure k of its annual Operational Risk losses in a horizon of T years. This involves a choice of k out of T years in which to apply the insurance policy coverage by making claims against losses in the given year. The…
Estimation of the operational risk capital under the Loss Distribution Approach requires evaluation of aggregate (compound) loss distributions which is one of the classic problems in risk theory. Closed-form solutions are not available for the distributions typically used in operational risk. However with modern comput…
Closed-form flow matching yields similar performance to stochastic version, improving model performance.
problem Understanding why flow matching models generalize well.
method Empirical analysis and comparison of stochastic and closed-form flow matching losses.
result Closed-form flow matching can improve model performance.
The paper examines optimal insurance design using Lambda-Value-at-Risk.
problem Optimal insurance design based on Lambda-Value-at-Risk.
method Analyzes optimal insurance solutions using Lambda-Value-at-Risk and closed-form expressions.
result Truncated stop-loss indemnity is optimal under certain conditions.
Unified framework approximates gradient descent's implicit bias in high dimensions.
problem Understanding gradient descent's behavior in overparameterized settings with convex losses.
method Unified framework for convex losses, including sensitivity analysis.
result Approximation of minimum-norm interpolation in high dimensions.
Optimizes neural networks' last layer with closed-form solutions.
problem Optimizing neural networks' last layer with stochastic gradient descent.
method Adapting closed-form last layer optimization for stochastic gradient descent, alternating between backbone and last layer updates.
result The method converges to optimal solutions and outperforms standard SGD and Adam in regression tasks.
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical Lp losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance. These losses are closely related to the …
New risk class defined based on loss location and deviation.
problem Risk assessment in loss distributions.
method Wrapper around smooth loss functions, M-estimators, stochastic gradient methods.
result Finite-sample stationarity guarantees for stochastic gradient methods.
Under the Basel II standards, the Operational Risk (OpRisk) advanced measurement approach allows a provision for reduction of capital as a result of insurance mitigation of up to 20%. This paper studies the behaviour of different insurance policies in the context of capital reduction for a range of possible extreme los…
A new method learns features for one-class classification using intra-class splitting.
problem Challenges in one-class classification due to limited normal class samples.
method Intra-class splitting and joint training of typical and atypical samples with loss functions.
result The method outperforms other models in one-class classification tasks.
In this paper, we address the aggregation of dependent stop loss reinsurance risks where the dependence among the ceding insurer(s) risks is governed by the Sarmanov distribution and each individual risk belongs to the class of Erlang mixtures. We investigate the effects of the ceding insurer(s) risk dependencies on th…
Paper establishes a formula linking model performance to insurance loss ratio.
problem Improving model performance does not always lead to proportional improvements in loss ratio.
method Derives a closed-form formula connecting Pearson correlation to expected loss ratio.
result Model improvements have diminishing marginal returns in reducing loss ratio.
A new Branch-and-Bound solver tackles L0-penalized problems with flexible loss functions.
problem Solving L0-penalized optimization problems with a broader class of loss functions.
method Generic Branch-and-Bound procedure with closed-form expressions for key quantities.
result El0ps solver achieves state-of-the-art performance and extends computational feasibility.
We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous path on which the cross-entropy loss is non-increasing and gets arbitrarily clos…
Previous research has shown that for stock indices, the most likely time until a return of a particular size has been observed is longer for gains than for losses. We establish that this so-called gain/loss asymmetry is present also for individual stocks and show that the phenomenon is closely linked to the well-known …
Modeling short selling risks to quantify losses.
problem Short selling constraints and associated risks.
method Optimal stopping model with margin risk and recall risk.
result Realistic short selling constraints lead to significant value loss.
The study finds a trade-off between model size, test loss, and training loss for linear predictors.
problem Finding the optimal balance between model size, test loss, and training loss for linear predictors.
method Established an algorithm and distribution-independent trade-off using non-asymptotic analysis.
result Models with low test loss are either classical (close to noise level training loss) or modern (large number of parameters).
Online trading platforms manipulate profits and losses, causing 82% of retail traders to lose money.
problem Manipulation of online trading platforms leading to financial losses for retail traders.
method Independent recording of trade details using REST API responses, comparison with broker reviews.
result 82% of retail traders lose money due to platform technical issues.
Study asset pricing with reference-dependent preferences, finding matching equity premia.
problem Understanding asset pricing under reference-dependent preferences.
method Discrete-time consumption-based capital asset pricing model with reference-dependent preferences.
result Models can generate equity premia matching empirical estimates, showing procyclical price-dividend ratio and countercyclical equity premium.
Novel approach to universal online learning for bounded losses, closing open problems.
problem Characterizing processes for universal online learning under non-i.i.d. conditions.
method Characterization of processes admitting strong and weak universal learning, introduction of optimistically universal learning rule.
result Introduction of a novel 1NN algorithm that is optimistically universal for bounded 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.
We stabilize MI-based losses by adding a regularization term, improving their performance and stability.
problem Instability of MI-based losses in machine learning.
method Added a novel regularization term to stabilize MI-based losses.
result Regularization stabilizes training and improves the performance of MI-based losses.
This paper extends stock trading results to include stop-loss orders.
problem Generalizing stock trading results with stop-loss orders.
method Geometric Brownian motion model, affine feedback controller, closed-form expression for cumulative distribution function.
result Affine feedback controller with stop-loss order generalizes results without stop-loss orders.
This work improves diffusion models by estimating the optimal loss value for better training diagnostics.
problem The optimal loss value of diffusion models is unknown and not indicative of absolute data-fitting quality.
method Derive the optimal loss in closed form and develop effective estimators, including a stochastic variant.
result Unlocking the optimal loss as a metric for diagnosing training quality of diffusion models.
We analyze the semi-hard triplet loss using Edgeworth expansion for better understanding of its behavior.
problem Understanding the behavior of the semi-hard triplet loss function.
method Developed a higher-order asymptotic analysis using the Edgeworth expansion.
result Derived explicit Edgeworth expansions revealing first-order corrections in terms of the third cumulant.
Focal loss improves classification but not class-posterior probability estimation.
problem Improving class-posterior probability estimation from focal loss.
method Proved classification-calibration and derived a transformation to recover true class-posterior probabilities.
result A transformation of the confidence score from focal loss minimization allows recovery of true class-posterior probabilities.
Paper tackles robust deep learning from weakly dependent data with unbounded loss and input.
problem Tackles robust deep learning from weakly dependent data with unbounded loss and input.
method Establishes non-asymptotic bounds for expected excess risk under strong mixing and ψ-weak dependence assumptions. result Derives a relationship between bounds and r, and shows convergence rate close to i.i.d. results for r=∞. Paper unifies bias and variance models for classification.
problem Different frameworks for bias and variance in classification.
method Unified Tumer & Ghosh and James approaches.
result Closed form relationships between 0/1 loss and squared error loss.
Proposes efficient Bayesian logistic regression for large sparse datasets.
problem Infeasibility of theoretical Bayesian methods for large sparse feature sets.
method Low complexity analytical approximations for sparse online logistic and probit regressions.
result Empirical results show superior performance compared to more complex methods.
This work analyzes when contrastive models are close to PCA or kernel methods.
problem Understanding when contrastive models are equivalent to kernel methods or PCA.
method Analyzing the training dynamics of two-layer contrastive models with non-linear activation.
result Wide contrastive models with cosine similarity based losses are close to PCA.
Paper proposes fitting loss functions to data using source functions from information geometry.
problem Choosing appropriate loss functions for machine learning models.
method Introduces source functions from information geometry to fit loss functions to the domain at hand.
result Significant improvements over state-of-the-art methods in model training.
Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalization may improve practical applications of deep networks. In this paper we show that with cross-entropy loss it is surprisingly simple to ind…
We discuss a short-time existence theorem of solutions to the initial value problem for a third order dispersive flow for closed curves into a compact almost Hermitian manifold. Our equations geometrically generalize a physical model describing the motion of vortex filament. The classical energy method cannot work for …
Proposes an alternative probabilistic interpretation of Huber loss.
problem Lack of intuitive understanding of Huber loss transition point.
method Relates Huber loss to Kullback-Leibler divergence between Laplace distributions.
result Identifies optimal transition point intuitively based on data noise.
Study on scalar curvature minimizability loss and saddle point solutions.
problem Loss of minimizability in prescribing scalar curvature.
method Variational approach, focusing on saddle point solutions.
result Existence of saddle point solutions despite minimizability loss.
New method prevents class collapse in metric learning with margin-based losses.
problem Class collapse in metric learning due to diverse intra-class samples.
method Proposed a sampling method to select nearest same-class samples as positive elements in tuple.
result Demonstrated clear benefits on various fine-grained image retrieval datasets.
Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations that scale linearly with the number of output classes, which can restrict the size of problems we are able to tackle with current hardware. Second, it remains unc…
Method learns graph-structured data segments using deep learning.
problem Segmenting data structured by an adjacency graph.
method Graph-structured contrastive loss for deep learning.
result Achieved state-of-the-art performance on 3D point cloud segmentation.
Sampling a fraction of pairs can match full evaluation in machine learning losses.
problem High computational cost of full pairwise loss evaluation.
method Survey sampling techniques targeting informative pairs.
result Performance close to full pairwise evaluation achieved with frugal sampling.
Study on proper learning under relaxed worst-case robust loss for VC classes.
problem Proper adversarially robust PAC learning under relaxed worst-case robust loss.
method Introduced a family of robust loss relaxations and showed their effectiveness for proper learnability.
result VC classes are properly PAC learnable with sample complexity close to standard PAC learning setup.
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An…
The paper compares different risk measures for optimal portfolio strategies.
problem Finding optimal portfolio strategies with various risk measures.
method Applying the Black-Scholes model and Martingale method to solve the static optimization problem.
result Comparison of different risk measures' performances on terminal wealths and optimal strategies.
The paper tackles performative risk optimization under weak convexity assumptions.
problem Optimizing performative risk in a closed-loop prediction system with weak convexity.
method Relaxing convexity assumptions to maintain optimization feasibility.
result Iterative optimization methods remain applicable even with weakened convexity conditions.
We find lower and upper bounds for the risk of estimating a manifold in Hausdorff distance under several models. We also show that there are close connections between manifold estimation and the problem of deconvolving a singular measure.
Positive results for agnostic regression with various losses.
problem Agnostic regression with bounded sample compression.
method Generic and efficient sample compression schemes for real-valued functions.
result Exact and approximate compression schemes for specific losses.
The Soft Nearest Neighbor Loss improves representation quality and generalization.
problem Improving the quality of representations in machine learning models.
method Explored and expanded the Soft Nearest Neighbor Loss to measure class entanglement.
result Maximizing the entanglement of different class representations leads to better generalization and uncertainty estimation.
The logcosh loss function helps neural networks learn set-valued functions better.
problem Learning set-valued functions with neural networks.
method Using artificial neural networks with logcosh loss.
result Neural networks with logcosh loss can classify samples based on set-valued functions.