arXiv research

Fisher loss improves deep domain adaptation by learning discriminative within-class compact and between-class separable representations.

SoftAdapt dynamically adjusts loss weights for multi-part functions.

LALR adapts learning rate for faster convergence in regression and neural nets.

Optimizing full likelihoods adapts loss scales and shapes for robust modeling.

New algorithms avoid a dominant lower-order term in heavy-tailed loss settings.

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforceme…

Selective reinitialization improves adaptability of neural bandits in dynamic environments.

Domain adaptation provides a powerful set of model training techniques given domain-specific training data and supplemental data with unknown relevance. The techniques are useful when users need to develop models with data from varying sources, of varying quality, or from different time ranges. We build CrossTrainer, a…

Adaptive rerouting reshapes impacts of maritime chokepoint disruptions

A meta-learning method learns adaptive robust loss functions for noisy labels.

Paper proposes adaptive margin loss to improve few-shot learning.

This paper examines the role and efficiency of the non-convex loss functions for binary classification problems. In particular, we investigate how to design a simple and effective boosting algorithm that is robust to the outliers in the data. The analysis of the role of a particular non-convex loss for prediction accur…

This work includes a number of novel contributions for the multiple-source adaptation problem. We present new normalized solutions with strong theoretical guarantees for the cross-entropy loss and other similar losses. We also provide new guarantees that hold in the case where the conditional probabilities for the sour…

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in existing GPUs. MPT is typically used in combination with a technique called los…

We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which imp…

Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.

Novel loss functions improve decision tree learning from noisy data.

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), …

Introduces a new stochastic optimization method for deep learning.

A new method for tighter privacy loss accounting in adaptive analyses.

New algorithms reduce regret for convex bandits with small comparator norms.

Adapts Exp3 to adversarial bandits with delays and data.

A new privacy accountant for Gaussian differential privacy measures individual privacy losses.

KOALA optimizes neural networks by treating loss as noisy measurements.

Optimizes hybrid insurance contracts for heavy-tailed losses.

We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by conclusively improving the performance of Adam and Momentum optimizers. The enhanced op…

This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the domain adaptation methods based on adversarial learning. However, several disconnections still …

One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations. However, it is not always trivial to know if an auxiliary task will be helpful for the main task and when it could start hurting. We propose to use the cosine similarity be…

In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts. At each step of the online game several experts predict a function, and the learner has to efficiently aggregate these functional forecasts into a single forecast. We adapt basic mixable (and exponentially conc…

TripleSurv improves survival analysis by ranking samples with time-adaptive adjustments.

WAVE improves stability in reinforcement learning by adaptively weighting critic's loss.

Adaptive linear bandit algorithm with best-of-three-worlds regret bounds.

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function. We estimate the appropriate hinge loss margin with the expected energy of the target distribution, and derive princi…

AMORE uses neural operators to efficiently predict multiple thermochemical states in stiff chemical kinetics.

Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. In this paper we study how the choice of optimization algorithm influences the robustness of the resulting classifie…

A new method optimizes anomaly scoring from score distribution to improve AD performance.

AdaRound improves post-training quantization of neural networks.

Proposes novel losses for fine-grained categorical domain adaptation.

Adaptive conformal inference without data exchangeability assumptions.

Separable losses are inconsistent for structured prediction models.

Unified surrogate loss framework for multi-label learning with strong consistency guarantees.

Adaptive market maker curves minimize arbitrage losses in DeFi.

Paper proposes efficient pruning method for neural networks.

ASAM improves deep neural network generalization by adapting sharpness to scale.

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories compri…

Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency. Therefore, most of the earlier works have modified the score function of the Tr…

AdamL optimizes deep learning models by incorporating loss function information.

Nowadays, users open multiple accounts on social media platforms and e-commerce sites, expressing their personal preferences on different domains. However, users' behaviors change across domains, depending on the content that users interact with, such as movies, music, clothing and retail products. In this paper, we pr…