arXiv research

Improves adversarial robustness by constraining logits with a bounded function.

A new logit model derived from the Weibull manifold.

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

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

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, …

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 …

Logit regularization induces logit clustering, affecting classifier performance.

New method distills cloud models into edge-friendly ones.

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 …

Generative classifier derived from any discriminative classifier rejects illegal inputs.

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 …

New algorithm avoids spurious sharpness minimization for NLP models.

MANO normalizes logits to estimate test accuracy without labels.

AdaDetectGPT improves text authorship detection with statistical guarantees.

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

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 …

Logit distance bounds representational similarity of models.

This paper concerns a method of selecting a subset of features for a sequential logit model. Tanaka and Nakagawa (2014) proposed a mixed integer quadratic optimization formulation for solving the problem based on a quadratic approximation of the logistic loss function. However, since there is a significant gap between …

LAWN normalizes logits to improve deep network adaptability and generalization.

This paper provides a theoretical and computational justification of the long held claim that of the similarity of the probit and logit link functions often used in binary classification. Despite this widespread recognition of the strong similarities between these two link functions, very few (if any) researchers have …

Label smoothing improves model robustness against misspecification.

A neural network-based two-sample test improves classification accuracy.

New algorithm reduces switching costs in multinomial logit bandit problems.

Multinomial logit bandit is a sequential subset selection problem which arises in many applications. In each round, the player selects a $K$-cardinality subset from $N$ candidate items, and receives a reward which is governed by a {\it multinomial logit} (MNL) choice model considering both item utility and substitution…

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…

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

New algorithm reduces reinforcement learning regret by adapting to interaction variability.

ELM improves neural model embeddings for long-tail learning.

Paper tackles long-tailed labels in classification problems.

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…

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

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…

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

New method estimates sparse covariance matrices in logit mixtures.

Logit correction improves model performance by correcting spurious correlations.

The paper models network formation using mixed logit models.

Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point. During this process, the adversarial example can be further optimized…

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…

This paper introduces new loss functions for balanced multi-class classification.

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

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

DMNL bandits optimize assortment choices balancing relevance and diversity.

Simple regularization methods mimic adversarial training's robustness.

A new network model combines features of DCBM, LSM, and β-model, using a cancellation trick for parameter estimation.

As datasets capturing human choices grow in richness and scale -- particularly in online domains -- there is an increasing need for choice models that escape traditional choice-theoretic axioms such as regularity, stochastic transitivity, and Luce's choice axiom. In this work we introduce the Pairwise Choice Markov Cha…