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.
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 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.
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.
The use of orthogonal projections on high-dimensional input and target data in learning frameworks is studied. First, we investigate the relations between two standard objectives in dimension reduction, preservation of variance and of pairwise relative distances. Investigations of their asymptotic correlation as well a…
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.
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.
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.
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…
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…
Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifier are typically optimized such that outputs from the model over a set of input samples most closely…
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.
When optimizing against the mean loss over a distribution of predictions in the context of a regression task, then even if there is a distribution of targets the optimal prediction distribution is always a delta function at a single value. Methods of constructing generative models need to overcome this tendency. We con…
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.
Proposes Deep LTMLE for estimating dynamic treatment effects in longitudinal studies.
problem Estimating counterfactual mean outcomes under dynamic treatment policies in longitudinal settings.
method Uses a transformer architecture with temporal-difference learning for initial estimation, followed by TMLE correction and statistical inference.
result Demonstrates superior performance in complex, long-term scenarios compared to existing methods.
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.
Improved loss scaling for stochastic momentum algorithms in high dimensions.
problem Improving loss scaling for stochastic momentum algorithms in high dimensions.
method Dimension-adapted Nesterov acceleration (DANA) scales momentum hyperparameters based on model size and data complexity.
result DANA improves loss scaling exponents across various data and target complexities.
Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output softmax probabilities. In this work, we present interesting experimental results that …
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.
Improved sampling via learned diffusions using variational losses.
problem Sampling from target distributions without direct access to samples.
method Generalized Schrödinger bridge problem, variational formulation, gradient-based optimization.
result Proposed log-variance loss leads to improved performance.
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.
Paper develops upper-bounds for target general loss in multiple source DA and DG settings.
problem Complexity and trade-offs in multiple source domain adaptation and domain generalization.
method Defines two types of domain-invariant representations and studies their pros, cons, and trade-offs.
result Developed upper-bounds for target general loss offer insights into domain-invariant representations.
Theoretical framework for target propagation shows differences from backpropagation.
problem Understanding and improving target propagation for neural networks.
method Mathematical optimization analysis and novel reconstruction loss.
result A novel reconstruction loss improves feedback weight training and introduces architectural flexibility.
New method recalibrates VaR for option books, reducing forecast errors.
problem Inaccurate VaR forecasts due to missing operational choices.
method Marking-aware sequential VaR recalibration targeting normalized book-level loss.
result Sequential VaR recalibration improves VaR performance across different markets and options.
In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same task. Given the limited availability of labelled examples in such tasks, we wish to make use of all the information we can. Usually a model le…
In this work we study loss functions for learning and evaluating probability distributions over large discrete domains. Unlike classification or regression where a wide variety of loss functions are used, in the distribution learning and density estimation literature, very few losses outside the dominant log loss ar…
Fisher loss improves deep domain adaptation by learning discriminative within-class compact and between-class separable representations.
problem Improving deep domain adaptation performance by learning discriminative representations.
method Proposes a Fisher loss to learn discriminative representations that are within-class compact and between-class separable.
result Noticeable improvements in deep domain adaptation performance, e.g., 6.67% absolute improvement in mean accuracy on the Office-Home dataset.
This work analyzes two methods for combining multiple binary labels in bipartite ranking.
problem Combining multiple binary labels for optimal bipartite ranking.
method Loss aggregation vs. label aggregation approaches.
result Label aggregation is preferable to loss aggregation due to label dictatorship issues.
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.
We study a stochastic game where one player tries to find a strategy such that the state process reaches a target of controlled-loss-type, no matter which action is chosen by the other player. We provide, in a general setup, a relaxed geometric dynamic programming principle for this problem and derive, for the case of …
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.
dGAP learns feature dependencies and predicts targets simultaneously.
problem Learning task-agnostic statistical dependencies and missing explicit feature dependencies.
method Jointly optimizes a neural dependency graph and target prediction loss.
result dGAP can recover correct feature dependencies and improve prediction accuracy.
This paper examines the Histogram Loss for regression, revealing its effectiveness without needing complex tuning.
problem Improving regression models by learning the entire distribution.
method Investigates Histogram Loss, a method that minimizes cross-entropy between a target distribution and a histogram prediction.
result The performance gain in regression models using Histogram Loss comes from optimization improvements, not extra modeling.
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…
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.
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 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.
Improves domain adaptation by aligning source and target distributions and mitigating noisy labels.
problem Improving performance on target images with different acquisition conditions.
method Combines optimal transport, MixUp regularization, and robust loss for noisy labels.
result Improves domain adaptation performance on various benchmarks and real-world problems.
There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such as by adding label noise, incorporating label ambiguity or using distillation. In…
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.
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…
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. Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper proposes and studies an approach, called feature-level domain adaptation (FLDA), …
A new method selects training samples for fine-tuning using validation set inference.
problem Selecting training examples for fine-tuning with limited target data.
method Invert train-validation roles; select samples affecting most predictions.
result Our method achieves lower test log-loss than state-of-the-art approaches.
The paper studies the loss landscape of regularized deep matrix factorization, revealing unique and sharp minimizers.
problem Understanding the loss landscape and minimizers of regularized deep matrix factorization problems.
method Theoretical analysis of ℓ2-regularized deep matrix factorization/deep linear network training problems with squared-error loss. result The unique end-to-end minimizer exists for all target matrices except for a set of Lebesgue measure zero.
We consider the following conditional linear regression problem: the task is to identify both (i) a k-DNF condition c and (ii) a linear rule f such that the probability of c is (approximately) at least some given bound μ, and f minimizes the ℓp loss of predicting the target z in the distribution of …
We introduce a hierarchical architecture for video understanding that exploits the structure of real world actions by capturing targets at different levels of granularity. We design the model such that it first learns simpler coarse-grained tasks, and then moves on to learn more fine-grained targets. The model is train…
This paper studies how to compress neural networks while maintaining accuracy.
problem Compressing a two-layer neural network with fewer nodes without losing accuracy.
method Using tools from high-dimensional probability, the authors minimize the L_2 loss between the target and compressed networks.
result The error rate of the approximation is shown as a function of input dimension and network size in the mean-field limit.