Study minimizes large losses in financial portfolios.
problem Minimizing large losses in financial portfolios.
method Generalizes quantile hedging approach for discrete and continuous time models.
result Generalized approach for minimizing large losses.
Study large deviations in life insurance portfolios without identical distributions.
problem Large deviations in life insurance portfolios with bounded losses and variances.
method Upper bound from standard large deviations, counterexample for full large deviation principle.
result Exponential bound for average loss exceeding a threshold.
Investigates conditions for risk or utility functionals to be sensitive to large losses.
problem Conditions for risk or utility functionals to be sensitive to large losses.
method Analyzes sensitivity to large losses for various risk and utility functionals.
result Value at Risk and Expected Shortfall generally fail to be sensitive to large losses, but expected utility functionals and certain adjusted versions are sensitive.
The paper examines how loss aversion impacts multi-armed bandit decisions over long periods.
problem The impact of loss aversion on multi-armed bandit decisions over long periods.
method A new central limit theorem for measures with history-dependent variances, derived under risk aversion in gains and risk loving in losses.
result Consequences of loss aversion for asymptotic properties are derived in analytical results.
Large learning rates improve neural network generalization, study shows.
problem Understanding why large learning rates lead to better neural network generalization.
method Visual analysis of training and testing loss landscapes, introduction of a nonlinear model.
result Extended phase with large learning rates leads to near-optimal generalization.
We prove a law of large numbers for the loss from default and use it for approximating the distribution of the loss from default in large, potentially heterogenous portfolios. The density of the limiting measure is shown to solve a non-linear SPDE, and the moments of the limiting measure are shown to satisfy an infinit…
Using particle system methodologies we study the propagation of financial distress in a network of firms facing credit risk. We investigate the phenomenon of a credit crisis and quantify the losses that a bank may suffer in a large credit portfolio. Applying a large deviation principle we compute the limiting distribut…
Analyzes loss correlations in overlapping credit portfolios, revealing significant risks.
problem Understanding mutual dependence of losses in large, overlapping credit portfolios.
method Analytical calculation of multivariate joint loss distribution using random matrix approach.
result Large concurrent portfolio losses and significant correlations are likely, even for small portfolios.
Locus scores predictions for risk, reducing large-loss events.
problem Deployment cost from inaccurate predictions, especially large losses.
method Distribution-free loss-scale reliability score using any predictive distribution.
result Reduces large-loss frequency compared to standard heuristics.
Paper establishes comparison theorems for large-margin learning.
problem Data piling issue in high-dimension and low-sample size SVM.
method Large-margin unified machines (LUM) loss functions.
result New comparison theorems for all LUM loss functions.
Proposes L-Softmax loss for CNNs to improve feature discriminativeness.
problem Lack of explicit feature discriminativeness in cross-entropy loss.
method Introduces L-Softmax loss that encourages intra-class compactness and inter-class separability.
result Deeply learned features with L-Softmax loss are more discriminative, boosting performance.
A new method for efficient label retrieval in large output spaces.
problem Efficiently retrieving relevant labels for inputs with large output spaces.
method Developed a technique called Stochastic Negative Mining to address the problem of set-valued classifiers in large output spaces.
result Stochastic Negative Mining outperforms existing negative sampling approaches in experiments.
Large stepsize GD for logistic regression converges faster than expected.
problem Optimizing logistic regression with large step sizes.
method Gradient descent with large stepsize applied to logistic regression.
result GD converges to a lower loss in fewer steps than expected.
GNC smooths loss function for large-batch SGD, improving generalization.
problem Extremely large-batch SGD leads to poor generalization and converges to sharp minima.
method Gradient noise convolution (GNC) smooths loss function by convolving gradient noise with the loss function.
result GNC achieves state-of-the-art generalization performance for large-scale deep neural networks.
New DAM method improves AUC scores in medical image classification.
problem Maximizing AUC in large-scale medical image classification.
method Proposes AUC margin loss for robust optimization, conducts extensive empirical studies.
result Improves performance on four medical image classification tasks, achieving 1st place on Stanford CheXpert.
The paper examines the unexpected losses and risk ratios for co-monotonic alternatives in large portfolios.
problem Understanding the unexpected losses and risk ratios for large portfolios with co-monotonic alternatives.
method Analyzes the asymptotic behavior of unexpected losses and risk ratios for co-monotonic alternatives using monotone cash-additive risk measures and Choquet insurance premia.
result Unexpected losses of large weighted portfolios are of order o(nλn), where λn is the average weight. We study the impact of contagion in a network of firms facing credit risk. We describe an intensity based model where the homogeneity assumption is broken by introducing a random environment that makes it possible to take into account the idiosyncratic characteristics of the firms. We shall see that our model goes behi…
Unified model predicts structure of neural network loss landscapes.
problem Understanding the structure of neural network loss landscapes.
method Modeling loss landscape as high-dimensional wedges, analyzing hyperparameters' effects.
result Existence of low-loss subspaces connecting solutions.
Study shows deep linear networks can converge to flatter minima at large learning rates.
problem Understanding the implicit bias of deep linear networks at large learning rates.
method Characterization of deep linear networks for binary classification using logistic loss in the large learning rate regime.
result Gradient descent iterates converge to a flatter minimum in the catapult phase for certain data separation conditions.
This paper improves loss functions for deep learning with noisy labels.
problem Training deep neural networks with noisy labels.
method The paper introduces a normalization technique to make any loss function robust to noisy labels and proposes a framework called Active Passive Loss (APL) to combine robust loss functions.
result The proposed APL framework consistently outperforms state-of-the-art methods, especially under high noise rates.
Method generates plausible financial stress scenarios using large deviations.
problem Misleading risk management by overlooking or overemphasizing implausible scenarios.
method Exploits large-deviations principle to concentrate risk factors near most likely stress configurations.
result Can generate informative stress scenarios even with limited historical data.
The study examines the statistical dependence of concurrent portfolio losses in non-overlapping credit portfolios.
problem Exploring the statistical dependence structure of concurrent portfolio losses in non-overlapping credit portfolios.
method Estimating empirical pairwise copulas to explore the dependence structure, finding asymmetry in copulas, and analyzing portfolio size effects.
result Concurrent large portfolio losses are more likely than small ones, and medium-sized and small portfolios exhibit notable correlations.
New loss functions improve extreme classification with missing labels.
problem Large number of infrequent labels and missing labels in XMC.
method Derive unbiased loss functions for XMC, incorporating them into existing algorithms.
result Significant improvement in extreme classification performance (up to 20%) over existing methods.
Efficient algorithms for large-scale multiclass classification with linear classifiers.
problem Training ℓ1-regularized linear classifiers with high dimensionality and many classes. method Combines quasi-bilinear objective, stochastic mirror descent, and non-uniform sampling.
result Proposes a sublinear algorithm for multiclass hinge loss.
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.
Efficiently decomposes large tensors using stochastic gradients.
problem Efficiently decomposing large tensors for multiway data analysis.
method Stochastic gradients computed via MTTKRP kernel for efficient computation.
result Advantages and scalability demonstrated for large-scale problems.
Paper connects sampling and labeling biases in large-output spaces.
problem Efficient training in large-output spaces with label imbalance.
method Unified approach to address sampling and labeling biases.
result Different negative sampling schemes trade-off performance on dominant and rare labels.
This paper examines how different loss functions affect neural network features and performance.
problem Investigating which loss function is best for deep neural networks.
method Examining last-layer features of deep networks and drawing inspiration from the Neural Collapse phenomenon.
result All relevant loss functions (CE, LS, FL, MSE) produce equivalent features and similar performance.
The study explores loss functions for learning distributions, finding the log loss and others are sufficient under certain conditions.
problem Understanding loss functions for distribution learning and density estimation.
method An axiomatic approach to design loss functions, proposing criteria and showing that no single loss function satisfies all criteria.
result No loss function satisfies all criteria, but the log loss and others do under the condition of candidate distributions being calibrated.
SGD with large learning rates can achieve better test accuracy than expected.
problem SGD with large learning rates often outperforms expected convergence bounds.
method Proved that SGD with small learning rates stays close to gradient flow path on modified loss.
result Explicitly adding an implicit regularizer to the loss improves test accuracy.
This paper improves compression of large NLP models using doped Kronecker Products.
problem Accuracy loss when compressing large NLP tasks with Kronecker Products.
method Doping Kronecker Products with an overlay matrix to recover accuracy, and a new regularization scheme called co matrix dropout regularization (CMR).
result Compression of a large language model with LSTM layers of size 25 MB by 25x with 1.4% loss in perplexity score.
Proposes a method to ensure low losses across all subpopulations in large datasets.
problem Standard practice of minimizing average loss fails to guarantee low losses across all subpopulations in heterogeneous datasets.
method Convex procedure that controls worst-case performance over all subpopulations of a given size with finite-sample convergence guarantees.
result Empirically, the worst-case procedure learns models that do well against unseen subpopulations.
New algorithms estimate Jacobian matrices for large-scale machine learning.
problem Efficiently computing search directions for large nonlinear least squares.
method Exploit low-rank structure in Hessian to estimate Jacobian matrices.
result Two algorithms perform well compared to state-of-the-art methods.
Study fast mean-reversion in large portfolios of stochastic volatility models for accurate loss estimation.
problem Estimating loss from large portfolios of stochastic volatility models with fast mean-reversion.
method Analyzes SPDEs and convergence of stochastic initial-boundary value problems under fast mean-reversion of volatility.
result Accurate estimation of loss distribution using approximate constant volatility models.
Paper proposes a novel method to improve matrix completion with median loss for large datasets.
problem Matrix completion with absolute deviation loss for large-scale data.
method Proposes a refinement step using pseudo data to improve inefficient estimators of median matrix completion.
result Turns inefficient estimators into a rate (near-)optimal matrix completion procedure.
New binary loss functions improve density ratio estimation accuracy.
problem Improving accuracy of density ratio estimators using binary classifiers.
method Characterized loss functions based on prescribed error measures in Bregman divergences.
result Novel loss functions prioritize accurate estimation of large density ratio values.
Photo-realistic super-resolution using GANs for large upscaling factors.
problem Recovering fine texture details at large upscaling factors.
method SRGAN, a GAN framework with adversarial and content losses.
result Significantly improved perceptual quality compared to state-of-the-art methods.
SIFT reduces training time by selecting samples with approximate losses.
problem Reducing training time by selecting samples with large approximate losses.
method Developed SIFT which uses early exiting to obtain approximate losses with intermediate layer representations for sample selection.
result SIFT achieves significant gains in training time and number of backpropagation steps without optimized implementation.
Introduces a differentiable approximation to the zero-one loss.
problem Incompatibility of zero-one loss with gradient-based optimization.
method Smooth projection onto hypersimplex through constrained optimization.
result Achieves significant improvements in generalization under large-batch training.
As it is known in the finance risk and macroeconomics literature, risk-sharing in large portfolios may increase the probability of creation of default clusters and of systemic risk. We review recent developments on mathematical and computational tools for the quantification of such phenomena. Limiting analysis such as …
NARME loss function speeds up neural network training for regression models.
problem Training neural networks on large datasets is time-consuming.
method Introducing Nth Absolute Root Mean Error (NARME) loss function.
result NARME reduces training time by up to 90% compared to other loss functions.
SGD explores loss surface by bouncing between valley walls, aiding generalization.
problem Understanding SGD's role in over-parametrized DNNs.
method Interpolating loss surface between consecutive SGD iterations, tracking metrics.
result SGD moves in valley-like regions, jumping between walls at a height above the valley floor.
Poisson learning doesn't solve graph semi-supervised learning issues.
problem Global information loss in graph-based semi-supervised learning.
method Poisson learning is Laplace regularization with thresholding.
result Poisson learning cannot overcome the global information loss problem.
Improves few-shot learning by adding a large margin to metric-based methods.
problem Few-shot learning's challenge of generalizing well with limited data.
method Unified framework with large margin distance loss function.
result Significant performance improvement with minimal computational overhead.
Study minimax rates for nonparametric density estimation with adversarial losses.
problem Estimating densities under various adversarial loss functions.
method General framework for analyzing minimax rates with different loss functions.
result Determines the minimax rate based on loss choice and density smoothness.
Loss minimization leads to multicalibration for neural networks.
problem Ensuring fairness in predictions across multiple protected groups.
method Minimizing squared loss over neural networks of size n.
result Minimizing loss over neural nets of size n implies multicalibration for most values of n.
LLMs learn peaked distributions slowly due to power-law losses.
problem Slow convergence of loss in training large language models.
method Systematic analysis of toy models and empirical evaluation of LLMs.
result Power-law time scaling with an exponent of 1/3 for learning peaked distributions.
Improved language identification with tuplemax loss.
problem Language identification with user-specified small sets of languages.
method Replaced softmax loss with tuplemax loss.
result 2.33% error rate improvement over softmax loss.