arXiv research

A new logit model derived from the Weibull manifold.

Deep learning classifiers are known to be vulnerable to adversarial examples. A recent paper presented at ICML 2019 proposed a statistical test detection method based on the observation that logits of noisy adversarial examples are biased toward the true class. The method is evaluated on CIFAR-10 dataset and is shown t…

Generative classifiers have been shown promising to detect illegal inputs including adversarial examples and out-of-distribution samples. Supervised Deep Infomax~(SDIM) is a scalable end-to-end framework to learn generative classifiers. In this paper, we propose a modification of SDIM termed SDIM-\emph{logit}. Instead …

AdaDetectGPT improves text authorship detection with statistical guarantees.

Optimal design for multinomial logit models improves assortment selection efficiency.

Paper tackles long-tailed labels in classification problems.

Logit models are usually applied when studying individual travel behavior, i.e., to predict travel mode choice and to gain behavioral insights on traveler preferences. Recently, some studies have applied machine learning to model travel mode choice and reported higher out-of-sample predictive accuracy than traditional …

Simple k-NN filtering improves model accuracy on noisy labels.

New algorithm avoids spurious sharpness minimization for NLP models.

Logit regularization induces logit clustering, affecting classifier performance.

Improves adversarial robustness by constraining logits with a bounded function.

The paper proposes a method to test properties of the optimal assortment in multinomial logit models.

Logit-GFN accelerates GFlowNets training by scaling logits based on temperature.

Proposes SOVR loss to improve adversarial robustness by increasing logit margins.

In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investigate whether it remains effective in this setting - an important open scientific question (Athalye et …

Logit dynamics formula reveals self-regulation in softmax policy gradient methods.

Proposes a convex model for mixed logit to handle individual heterogeneity.

Recently, Kannan et al. [2018] proposed several logit regularization methods to improve the adversarial robustness of classifiers. We show that the computationally fast methods they propose - Clean Logit Pairing (CLP) and Logit Squeezing (LSQ) - just make the gradient-based optimization problem of crafting adversarial …

Develops a power-calibrated framework for LLM watermarking, optimizing tradeoffs between detectability and distortion.

The recent success of generative adversarial networks and variational learning suggests training a classifier network may work well in addressing the classical two-sample problem. Network-based tests have the computational advantage that the algorithm scales to large samples. This paper proposes a two-sample statistic …

MANO normalizes logits to estimate test accuracy without labels.

The paper provides guarantees for a tangent transform algorithm in logistic regression models.

New method uses low logit rank to simplify complex language models.

Logit distance bounds representational similarity of models.

DMNL bandits optimize assortment choices balancing relevance and diversity.

We consider neural network training, in applications in which there are many possible classes, but at test-time, the task is a binary classification task of determining whether the given example belongs to a specific class, where the class of interest can be different each time the classifier is applied. For instance, …

The paper develops a statistical theory explaining overfitting in imbalanced classification.

LAWN normalizes logits to improve deep network adaptability and generalization.

BoC probe assesses neural network confidence coherence, revealing architecture-specific uncertainty.

New algorithm reduces switching costs in multinomial logit bandit problems.

We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model in which the defense is considered. We provide a brief overview of the defense and the threat models…

ELM improves neural model embeddings for long-tail learning.

Annealing Double-Head calibrates deep neural networks during training.

New method distills cloud models into edge-friendly ones.

New algorithm tackles non-linear utility in MNL bandits with $ilde{O}(\sqrt{T})$ regret.

The standard Gibbs sampler of Mixed Multinomial Logit (MMNL) models involves sampling from conditional densities of utility parameters using Metropolis-Hastings (MH) algorithm due to unavailability of conjugate prior for logit kernel. To address this non-conjugacy concern, we propose the application of Pólygamma data a…

The paper proposes an efficient method to scale Bayesian inference for mixed multinomial logit models to very large datasets.

Proposes a new model for context-dependent decision-making.

Logit correction improves model performance by correcting spurious correlations.

This article presents a proof of the existence of Bertrand-Nash equilibrium prices with multi-product firms and under the Logit model of demand that does not rely on restrictive assumptions on product characteristics, firm homogeneity or symmetry, product costs, or linearity of the utility function. The proof is based …

The paper models network formation using mixed logit models.

The paper characterizes the efficiency of transferring knowledge from a teacher to a student classifier over finite domains.

The paper calibrates uncertainty in dropout variational inference models.

In discrete choice modeling (DCM), model misspecifications may lead to limited predictability and biased parameter estimates. In this paper, we propose a new approach for estimating choice models in which we divide the systematic part of the utility specification into (i) a knowledge-driven part, and (ii) a data-driven…

Analyzes how inclusion/exclusion from STOXX Europe 600 Index affects company prices.

WEINCE improves contrastive learning by correcting softmax biases.

Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.

New lower bounds improve logistic log-likelihood optimization and inference.