arXiv research

Proposes LML layer for multi-label predictions with k labels.

New approaches estimate recommendation metrics using sampling.

Paper analyzes trade-offs in top-k classification accuracies and proposes a new loss function.

Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evaluate classifiers based on the top-k error instead of the standard zero-one loss. We propose top-k multiclass SVM as a direct method to optimiz…

The top-$k$ error is often employed to evaluate performance for challenging classification tasks in computer vision as it is designed to compensate for ambiguity in ground truth labels. This practical success motivates our theoretical analysis of consistent top-$k$ classification. Surprisingly, it is not rigorously und…

Paper introduces a new loss function for deep imbalanced classification.

Smoothed top-k operator improves model training efficiency.

Paper introduces efficient top-k selection with differential privacy.

Motivated by applications in recommender systems, web search, social choice and crowdsourcing, we consider the problem of identifying the set of top $K$ items from noisy pairwise comparisons. In our setting, we are non-actively given $r$ pairwise comparisons between each pair of $n$ items, where each comparison has noi…

In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity between the class labels, raising the question if top-1 error is the right perf…

Online boosting for multilabel ranking with limited feedback.

Unified model for prediction and deferral selects top-k entities efficiently.

Paper characterizes minimax regret rates for online ranking with top-k feedback.

Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two direc…

Paper introduces MPES for top-k ranking BO with preferential observations.

Study improves top-k set prediction with low cardinality.

Paper extends top-k Mallows model for better user preference analysis.

Top-k sparsification reduces deep learning communication costs.

Proposes differentiable and sparse top-k operators for neural networks.

Work on making classifiers robust against adversarial attacks for top-k predictions.

This paper compares average-K and top-K classification methods under ambiguity.

Study on top-$k$ classification with new loss functions and algorithms.

This paper explores the preference-based top-$K$ rank aggregation problem. Suppose that a collection of items is repeatedly compared in pairs, and one wishes to recover a consistent ordering that emphasizes the top-$K$ ranked items, based on partially revealed preferences. We focus on the Bradley-Terry-Luce (BTL) model…

The paper proposes methods to identify and sample from mixtures of Mallows models for top-k rankings.

Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.

New method makes CNN interpretations robust to adversarial attacks.

Introduces top-$k$ regularization for better feature selection in machine learning.

New insights into the top-K sparse softmax gating function for deep learning.

We study the top-$K$ ranking problem where the goal is to recover the set of top-$K$ ranked items out of a large collection of items based on partially revealed preferences. We consider an adversarial crowdsourced setting where there are two population sets, and pairwise comparison samples drawn from one of the populat…

Optimizes ranking of top-k players from partial comparison data.

Optimizes identifying top-k items from comparisons with minimal comparisons.

The paper addresses calibration in label ranking, a structured prediction task.

New framework for optimizing machine learning risks.

We explore the top-$K$ rank aggregation problem. Suppose a collection of items is compared in pairs repeatedly, and we aim to recover a consistent ordering that focuses on the top-$K$ ranked items based on partially revealed preference information. We investigate the Bradley-Terry-Luce model in which one ranks items ac…

RAMPART ranks top-k features more accurately than existing methods.

Proposes a method to infer ranking properties and top-K rankings with uncertainty quantification.

We study the active learning problem of top-$k$ ranking from multi-wise comparisons under the popular multinomial logit model. Our goal is to identify the top-$k$ items with high probability by adaptively querying sets for comparisons and observing the noisy output of the most preferred item from each comparison. To ac…

New sparsity operator reduces variance reduction methods' computational cost.

This paper explores the adaptive (active) PAC (probably approximately correct) top-$k$ ranking (i.e., top-$k$ item selection) and total ranking problems from $l$-wise ($l\geq 2$) comparisons under the multinomial logit (MNL) model. By adaptively choosing sets to query and observing the noisy output of the most favored …

Top-k Combinatorial Bandits generalize multi-armed bandits, where at each round any subset of $k$ out of $n$ arms may be chosen and the sum of the rewards is gained. We address the full-bandit feedback, in which the agent observes only the sum of rewards, in contrast to the semi-bandit feedback, in which the agent obse…

New algorithm reduces online learning regret for bounded recall games.

This paper introduces a new method to train normalizing flows using precision-recall divergences.

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, especially white-box targeted attacks. One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e.g., the Carlini-Wagner (C&W) method). Most methods address targ…

In this work, we introduce the {\em average top-$k$} (\atk) loss as a new aggregate loss for supervised learning, which is the average over the $k$ largest individual losses over a training dataset. We show that the \atk loss is a natural generalization of the two widely used aggregate losses, namely the average loss a…

Recurrent models can produce infinite sequences, causing bias; new methods prevent this.

A simple modification improves GAN performance by discarding bad samples.

New methods provide stable ranking without assumptions on data distributions.

We define the stabilizing number $\operatorname{sn}(K)$ of a knot $K \subset S^3$ as the minimal number $n$ of $S^2 \times S^2$ connected summands required for $K$ to bound a nullhomotopic locally flat disc in $D^4 \# n S^2 \times S^2$. This quantity is defined when the Arf invariant of $K$ is zero. We show that $\oper…