Orthogonal projections improve learning accuracy in clinical image segmentation and music classification.
problem Improving accuracy in learning tasks with high-dimensional data.
method Investigation and application of orthogonal projections to balance variance and pairwise distances in dimension reduction. Extension to deep learning with augmented target loss functions.
result Augmented target loss functions increase accuracy in clinical image segmentation and music classification.
Paper proposes a new loss function for conditional models using soft targets.
problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.
This paper consider penalized empirical loss minimization of convex loss functions with unknown non-linear target functions. Using the elastic net penalty we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear this inequali…
This research finds that using mean-squared error and codeword targets improves adversarial robustness.
problem Evaluating and improving the robustness of neural networks against adversarial attacks.
method Training neural networks on mean-squared error and using codeword targets as representations.
result The modified models show up to 98.7% increase in accuracy against untargeted attacks and up to 99.8% decrease in targeted attack success rates.
Structured entropy improves classification performance on structured targets.
problem Cross-entropy loss fails to account for target variable structure.
method Proposes structured entropy, a generalization of entropy using random partitions.
result Structured cross-entropy loss yields better results on classification problems with known structure.
HSIC loss improves robust regression and classification models.
problem Learning robust models in the absence of target domain data.
method Adapted HSIC loss for unsupervised covariate shift.
result Models outperform standard methods on covariate shift tasks.
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.
SCA learns to learn from target-set examples, improving few-shot learning performance.
problem Limited labelled examples in few-shot learning tasks.
method SCA learns a label-free loss function via self-critique and adapts the base-model for new tasks.
result SCA achieves substantially reduced error-rates and state-of-the-art performance.
Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution. However, often we do not have direct access to our target distribution - our data may be subject to sample selection bias, or may be from a different but related distribution. W…
We present a powerful new loss function and training scheme for learning binary hash codes with any differentiable model and similarity function. Our loss function improves over prior methods by using log likelihood loss on top of an accurate approximation for the probability that two inputs fall within a Hamming dista…
Proves existence of optimal shallow neural networks with ReLU activation.
problem Proving the existence of optimal shallow feedforward networks with ReLU activation.
method Proves existence of global minima in the loss landscape for continuous target functions using shallow feedforward neural networks with ReLU activation.
result Existence of global minima in the loss landscape for shallow feedforward networks with ReLU activation.
Study examines CSO algorithm for 3D swarming and tracking multiple targets.
problem Simulating and tracking multiple targets in 3D space.
method Cyclic Stochastic Optimization (CSO) algorithm implemented by mobile sensing agents.
result CSO algorithm converges in 3D space, minimizing uncertainty in targets' state estimates.
Enhances ENet's prediction accuracy while maintaining uncertainty estimation.
problem Gradient shrinkage problem in ENet's loss function.
method Proposes a multi-task learning framework with a modified MSE loss function.
result Improves ENet's prediction accuracy without losing uncertainty estimation.
Generative models learn to capture target distribution support with extreme value loss.
problem Mode collapse in generative models for non-trivial target distributions.
method Optimizing against the minimal value of the loss function, rather than the mean.
result Models trained with extreme value loss learn to capture the support of the target distribution.
Paper explains learning property of logistic and softmax losses for balanced and imbalanced class data.
problem Understanding and optimizing loss functions for deep neural networks with class imbalances.
method Analyzing necessary conditions for convergence of logistic and softmax losses in CNNs.
result Proposes a novel reweighted logistic loss function that improves performance over softmax loss.
New bounds show polyhedral surrogates are optimal for generalization.
problem Proving generalization rates for polyhedral loss functions.
method Developed two general results for polyhedral surrogates.
result Polyhedral surrogates provide linear surrogate regret bounds, translating directly to target rates.
We study prediction and estimation problems using empirical risk minimization, relative to a general convex loss function. We obtain sharp error rates even when concentration is false or is very restricted, for example, in heavy-tailed scenarios. Our results show that the error rate depends on two parameters: one captu…
A novel minimax classifier tackles imbalanced datasets with few minority samples.
problem Imbalanced datasets with limited minority samples.
method Proposes a novel minimax learning algorithm with two steps: minimization and maximization.
result The algorithm improves model performance compared to existing methods.
Optimal unimodal fitting for linear loss functions in a sequential, efficient manner.
problem Optimal unimodal transformation of univariate model scores under linear loss functions.
method Proposes a sequential approach to estimate the optimal rectangular fit for observed samples with each new sample.
result Sequential approach achieves optimal efficiency with logarithmic time complexity per iteration.
Introduces Fitzpatrick losses, tighter than Fenchel-Young losses.
problem Improving loss functions for machine learning.
method Introduces Fitzpatrick losses based on the Fitzpatrick function.
result Fitzpatrick losses are tighter than Fenchel-Young losses.
Proposes a new method for estimating non-pathwise differentiable functional parameters.
problem Estimating dose-response curves for continuous exposure.
method Targeted Highly Adaptive Lasso (HAL) for non-pathwise differentiable functional parameters.
result The Targeted HAL-MLE achieves dimension-free rates up to log(n) factors and outperforms other methods in simulations.
Paper introduces a new robust loss function for RL.
problem Heuristic selection of threshold parameters in quantile Huber loss.
method Derived from Wasserstein distance, captures noise in quantile values.
result Enhances robustness against outliers and enables parameter adjustment.
Label smoothing improves model robustness against misspecification.
problem Improving model robustness against model misspecification.
method Introducing modified label smoothing (MLSLR) that maintains consistent probability estimation while modifying the loss function.
result MLSLR exhibits higher robustness against model misspecification than conventional label smoothing.
New loss function optimization improves training speed and accuracy.
problem Optimizing neural network performance through loss functions.
method Genetic Loss-function Optimization (GLO) using genetic programming and CMA-ES.
result GLO loss functions lead to better performance with fewer training steps.
We study proper losses for discrete generative models without knowing the target distribution.
problem Evaluating generative models in the discrete setting without direct access to the target distribution.
method Define and construct black-box proper losses using statistical estimation theory.
result Black-box proper losses must be of polynomial form and involve more samples than the polynomial degree.
Automates loss function selection for faster, more robust model training.
problem Manual selection of loss functions is inefficient and model-specific.
method Meta-learning to learn parametric loss functions that generalize across tasks.
result Meta-trained loss functions improve model performance in supervised and reinforcement learning.
This paper calculates worst-case target semi-variances for uncertain losses.
problem Managing risk when loss distribution is uncertain and only partial information is known.
method Derives worst-case target semi-variances for symmetric or non-negative losses under uncertainty sets representing investor's undesirable scenarios.
result Closed-form expressions for worst-case target semi-variances are derived.
Develops a direct debiased machine learning framework using Bregman divergence.
problem Reduces bias in machine learning estimates of causal effects or structural models.
method Neyman targeted estimation and generalized Riesz regression using Bregman divergence.
result Improves estimation of parameters of interest in causal models.
Sobolev training helps neural nets fit function values and derivatives.
problem Training neural nets to match function values and derivatives accurately.
method Using Sobolev loss with gradient flow for overparameterized networks.
result Gradient flow from random initialization can fit any function and its derivatives.
Paper proposes AXE loss for non-autoregressive machine translation, improving performance.
problem Challenges in training non-autoregressive models due to lack of autoregressive factors and cross entropy loss penalties.
method Proposes aligned cross entropy (AXE) loss function using a differentiable dynamic program for better word order alignment.
result AXE-based training improves performance on major WMT benchmarks and sets a new state of the art for non-autoregressive models.
TILT improves target domain performance by penalizing an auxiliary component on unlabeled target inputs.
problem Improving performance on target domain under covariate shift.
method TILT uses a novel objective function to decompose the source predictor and penalize an auxiliary component on unlabeled target inputs.
result TILT improves target domain performance over source-only training and other baselines.
Novel oracle-type inequality for logistic loss in DNNs achieves sharp convergence rates.
problem Generalization analysis for binary classification with DNNs and logistic loss.
method Established an oracle-type inequality to handle the boundedness of the target function.
result Optimal convergence rates for fully connected ReLU DNN classifiers trained with logistic loss.
Study on H-consistency bounds for machine learning surrogates.
problem Estimating target loss error relative to surrogate loss error in machine learning.
method Developed H-consistency bounds for various surrogates and loss functions. result Stronger guarantees than existing methods, offering distribution-dependent and -independent bounds.
We develop a new loss function for estimating quasiprobabilistic density ratios.
problem Discontinuous or non-surjective relationships between optimal classifiers and target densities.
method Introduce a convex loss function compatible with both probabilistic and quasiprobabilistic densities.
result Achieve state-of-the-art results in estimating di-Higgs production in particle physics.
Study improves top-k set prediction with low cardinality.
problem Improving top-k set prediction accuracy with low cardinality.
method Introduces new target loss function and surrogate losses.
result Demonstrates effectiveness of cardinality-aware algorithms.
A new method for representation and metric learning on manifolds boosts performance.
problem Improving representation and metric learning on complex, non-Euclidean data.
method Atlas-based manifold representation with a modified encoder and MMD loss.
result Substantial performance boost over baseline for low-dimensional encodings.
Diffusion models accurately recover mixture weights from generated samples despite score function insensitivity.
problem Score-based generative models often fail to learn correct relative mode amplitudes (mixture weights) from generated samples.
method Relate diffusion score matching (DSM) loss to mixture weight estimation error, define diffusion score sensitivity index (DSSI), and prove its governing role in mixture weight recovery.
result Generated samples can accurately recover mixture weights from the DSM loss, even when the target score is insensitive to mixture weights.
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.
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.
Paper proposes a novel framework for structure learning using unstructured kernel-based M-regression.
problem Identifying underlying structures of true target functions from observed data.
method General and novel framework using unstructured M-regression in RKHS, inspired by gradient functions.
result Asymptotic results established for a wide range of loss functions, including mean, quantile, likelihood, and margin-based methods.
Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that provide theoretical guarantees on why they are so effective. Lying in the center of…
Improves score estimation for noised targets using known clean scores.
problem Poor score estimation at low noise levels in Denoising Score Matching.
method Introduces Target Score Identity and Target Score Matching loss.
result Score estimates are more accurate at low noise levels.
A new method approximates loss functions asymmetrically to prevent catastrophic forgetting.
problem Catastrophic forgetting in deep neural networks.
method Approximating a true loss function using an asymmetric quadratic function with one side overestimated.
result Achieves state-of-the-art accuracy close to upper-bound performance on benchmark datasets.
Enhanced H-consistency bounds derived under relaxed conditions.
problem Quantifying the relationship between zero-one estimation error and surrogate loss estimation error.
method Relaxing the condition on the surrogate loss conditional regret and presenting a general framework for establishing enhanced H-consistency bounds. result Derivation of more favorable H-consistency bounds in various scenarios. A new method optimizes anomaly scoring from score distribution to improve AD performance.
problem Vulnerability to anomaly contamination and lack of adaptability in existing AD methods.
method Optimizes anomaly scoring function from score distribution perspective, using Overlap loss.
result Overlap loss-based AD models significantly outperform state-of-the-art methods.
Unified framework for automatic debiased machine learning for various statistical parameters.
problem Inference on smooth functionals of nonparametric M-estimands.
method Unified framework using gradient, Hessian, and linear approximation; solves two risk minimization problems.
result Efficient autoDML estimators with double robustness and robustness to misspecification.
New loss functions reveal layer roles in deep neural networks.
problem Understanding the role of individual layers in deep neural networks.
method Derived Deep Gaussian Layer-wise loss functions (DGLs) using Gaussian Processes and SGD.
result First explicit and competitive layer-wise loss functions for deep neural networks.
This paper addresses tracking of a moving target in a multi-agent network. The target follows a linear dynamics corrupted by an adversarial noise, i.e., the noise is not generated from a statistical distribution. The location of the target at each time induces a global time-varying loss function, and the global loss is…