This paper compares average-K and top-K classification methods under ambiguity.
problem Choosing a single label in ambiguous cases leads to low precision.
method Formally characterizes ambiguity profiles and compares average-K and top-K classification methods.
result Average-K can achieve lower error rates than top-K in some ambiguous cases.
A new loss function combines advantages of average and max losses for better adaptability.
problem Improving supervised learning performance across various data distributions.
method Introducing average top-k loss, a convex function that averages the top-k losses. result The \atk loss function can adapt better to different data distributions and is convex.
A new loss function improves classification accuracy in imbalanced datasets.
problem Suboptimal decision boundaries in classification with average, maximal, and average top-k losses. method Proposes a new classification objective called the close-k aggregate loss, which minimizes the loss for points close to the decision boundary. result Close-k aggregate loss achieves significant gains in 0-1 test accuracy compared to average, maximal, and average top-k losses. Top-k multiclass SVM optimizes for top-k error in ambiguous image classification.
problem Ambiguity in large-class image classification problems.
method Proposes a generalization of multiclass SVM to optimize for top-k error using a tight convex upper bound and efficient projection onto the top-k simplex.
result Consistent improvements in top-k accuracy compared to baselines on five datasets.
The paper analyzes top-k classification and proposes consistent loss functions.
problem Understanding consistency of top-k classification in challenging tasks.
method Theoretical analysis, defining top-k calibration, proposing new loss functions.
result Proposes a new consistent hinge loss and a top-k calibrated convex loss.
Paper analyzes trade-offs in top-k classification accuracies and proposes a new loss function.
problem CE loss does not always optimize top-k prediction, especially with complex data.
method Introduces a novel top-k transition loss to improve top-k accuracy.
result Our loss function improves top-k accuracy, especially for k > 10.
Paper evaluates and introduces new top-k loss functions for improved performance.
problem Increased ambiguity in modern datasets affects performance measures.
method Comparison and evaluation of multiclass methods, introduction of new top-k loss functions.
result Softmax loss performs well across all k, new top-k losses improve performance.
New algorithm for top-K ranking with linear time and competitive ratio of sqrt(n).
problem Identifying top K items from noisy pairwise comparisons.
method Linear time algorithm with competitive ratio of sqrt(n) under strong stochastic transitivity model.
result Tight competitive ratio of sqrt(n) for top-K ranking problem.
Paper introduces a new loss function for deep imbalanced classification.
problem Class ambiguity and imbalance in large datasets.
method Stochastic top-K hinge loss based on smoothed top-K operator.
result Our loss function significantly outperforms other baseline loss functions in imbalanced datasets.
Smoothed top-k operator improves model training efficiency.
problem Discontinuous top-k operation makes models untrainable end-to-end.
method SOFT top-k operator approximates top-k as EOT solution.
result Improved performance in k-nearest neighbors and beam search.
Study explores loss functions for multiclass, top-k, and multilabel classification.
problem Understanding and optimizing loss functions for multiclass, top-k, and multilabel classification.
method In-depth analysis of multiclass top-k methods, optimization of loss functions, and development of efficient training algorithms.
result Softmax and smooth multiclass SVM are competitive in top-k error across all k.
A new algorithm for selecting top-k arms in extreme contextual bandits with improved efficiency.
problem Selecting top-k arms from a large set with contextual information and limited rewards.
method Proposes an algorithm for both non-extreme and extreme settings, using Inverse Gap Weighting and arm hierarchy models.
result Achieves improved regret guarantees for extreme settings with significant computational and statistical efficiency.
Paper introduces efficient top-k selection with differential privacy.
problem Efficiently selecting top-k elements with differential privacy.
method Oneshot Laplace mechanism, generalizing Report Noisy Max.
result Noise level of O(sqrt(k)/eps) for approximate differential privacy.
Study top-K ranking with adversarial crowdsourced data, identifying top-K items reliably.
problem Recovering top-K ranked items from partially revealed preferences in an adversarial setting.
method Characterizes minimax limit on sample size for reliable identification, extends to unknown population size.
result Establishes fundamental limits on sample size for top-K recovery in adversarial crowdsourced data.
Online boosting for multilabel ranking with limited feedback.
problem Multilabel ranking with top-k feedback.
method Surrogate loss function and unbiased estimator for weak learners.
result Adapted full information multilabel ranking algorithms to top-k feedback setting with theoretical and experimental support.
Unified model for prediction and deferral selects top-k entities efficiently.
problem Efficiently selecting top-k entities for deferral in machine learning.
method One-stage Top-k Learning-to-Defer framework with a convex surrogate. result Unified model achieves superior accuracy-cost trade-offs.
Paper characterizes minimax regret rates for online ranking with top-k feedback.
problem Analyzing online ranking with partial feedback.
method Developed techniques from partial monitoring to characterize minimax regret rates.
result Full characterization of minimax regret rates for Precision@n.
Paper introduces MPES for top-k ranking BO with preferential observations.
problem Handling top-k ranking and tie/indifference observations in Bayesian optimization.
method Designs a surrogate model and introduces MPES acquisition function.
result MPES outperforms existing acquisition functions in handling preferential observations.
Study improves top-k set prediction with low cardinality.
problem Improving top-k set prediction accuracy with low cardinality.
method Introduces new target loss function and surrogate losses.
result Demonstrates effectiveness of cardinality-aware algorithms.
Paper extends top-k Mallows model for better user preference analysis.
problem Capturing real-world user preferences focusing on a limited set of items.
method Generalized top-k Mallows model, novel sampling scheme, efficient algorithm, active learning.
result New tools for analysis and prediction in decision-making scenarios.
Top-k sparsification reduces deep learning communication costs.
problem Reducing communication overhead in distributed deep learning.
method Extensive experiments and theoretical analysis of Top-k sparsification.
result A tighter bound for Top-k operator derived, improving scaling efficiency.
Proposes differentiable and sparse top-k operators for neural networks.
problem Discontinuity of top-k operator makes it unsuitable for end-to-end training with backpropagation.
method Formulates top-k as a linear program over permutahedron, introduces p-norm regularization, and uses isotonic optimization.
result Successfully applied to neural network pruning, fine-tuning, and routing.
Work on making classifiers robust against adversarial attacks for top-k predictions.
problem Vulnerability of classifiers to adversarial perturbations, especially for top-k predictions.
method Randomized smoothing to turn any classifier into a robust one, using Gaussian noise.
result Derives a tight robustness in ℓ2 norm for top-k predictions, achieving 62.8% certified top-5 accuracy on ImageNet.
Proposes LML layer for multi-label predictions with k labels.
problem Efficient multi-label prediction with limited labels.
method Probabilistic multi-label modeling, efficient forward and backward passes.
result Improves top-k recall and accuracy in multi-label tasks.
Study on top-k classification with new loss functions and algorithms.
problem Improving multi-class classification accuracy and cardinality trade-off.
method Introducing cardinality-aware loss functions and deriving their consistency bounds.
result New cardinality-aware algorithms for top-k classification. 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.
problem Identifying and sampling from mixtures of Mallows models for top-k rankings in a heterogeneous population.
method Efficient sampling algorithms and identifiability proofs for both components of the mixture.
result The identifiability and learnability of the Mallows components' parameters in the mixture.
Optimally ranks top-K items from pairwise comparisons.
problem Aggregating rankings from pairwise comparisons to focus on top-K items.
method Bradley-Terry-Luce model, spectral method.
result Spectral method achieves optimality in sample size for top-K ranking.
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
problem Limitation of existing L2D frameworks to single-expert deferral.
method Top-k Learning-to-Defer framework, including adaptive Top-k(x) variant. result Superior accuracy-cost trade-offs with multi-expert deferral.
New algorithm identifies top-k items with minimal comparisons.
problem Active learning of top-k rankings from noisy comparisons.
method Designs an instance-optimal algorithm without item score info.
result Achieves nearly instance optimal performance with matching lower bound.
New method makes CNN interpretations robust to adversarial attacks.
problem Adversarial attacks on CNN interpretation maps.
method Renyi Differential Privacy (RDP) for robust interpretation.
result Certifiable top-k robustness and improved experimental robustness. Introduces top-k regularization for better feature selection in machine learning.
problem Limited ability of existing feature selection methods to reconcile feature representativeness and inter-correlations.
method Top-k regularization, which induces a sub-architecture on the model's architecture to select informative features and model complex relationships. result Uniform approximation error bound for top-k regularization approximating high-dimensional sparse functions. New insights into the top-K sparse softmax gating function for deep learning.
problem Understanding the theoretical effects of the top-K sparse softmax gating function on density and parameter estimations.
method Using a Gaussian mixture of experts, novel loss functions, and theoretical analysis.
result The convergence rates of density and parameter estimations are parametric under certain conditions, but slow under over-specified models.
A2SGD reduces distributed SGD communication to O(1) per worker.
problem Heavy communication costs in distributed SGD for large models.
method Two-level gradient averaging to consolidate gradients to two local averages.
result Achieves O(1) communication complexity per worker, significantly reducing traffic and training time.
A new algorithm for top-k combinatorial bandits with full-bandit feedback.
problem Optimizing decisions among subsets of arms with only aggregate rewards observed.
method CSAR algorithm using Hadamard matrices for estimating individual arm rewards.
result Proved a tight lower bound on sample complexity for k=O(1). Optimizes ranking of top-k players from partial comparison data.
problem Identifying the top-k players from incomplete pairwise comparisons.
method Maximum Likelihood Estimator (MLE) and Spectral Method.
result MLE achieves optimal partial and exact recovery, while Spectral Method is sub-optimal.
Optimizes identifying top-k items from comparisons with minimal comparisons.
problem Finding the top-k items from pairwise comparisons with a fixed error rate.
method Developed an asymptotically optimal algorithm using primal-dual procedure and adaptive comparison allocation.
result Proves the algorithm is asymptotically optimal for top-k identification.
SNeCT integrates multi-platform genomic data using Tucker decomposition with network constraints.
problem Integrative analysis of large-scale, high-dimensional, sparse genomic data with prior knowledge incorporation.
method Parallel stochastic gradient descent on a network-constrained optimization function.
result Decomposed factor matrices stratify cancers, find similar patients, and personalize interpretation.
The paper addresses calibration in label ranking, a structured prediction task.
problem Calibration in label ranking is not well understood and often poorly calibrated.
method Formalized calibration for label ranking, developed a hierarchy of notions, and empirically evaluated models.
result Popular label ranking models are often poorly calibrated, with differences between sub-ranking and top-k metrics.
Proposes learning ordered Top-k attacks for image classification.
problem Vulnerability of DNNs to adversarial attacks, especially white-box targeted attacks.
method Adversarial distillation framework to compute adversarial probability distributions and minimize KL divergence.
result Outperforms C&W method in Top-1 and Top-5 settings for image classification.
A new algorithm improves top-k recommendation accuracy by considering item payoffs uncertainty.
problem Suboptimal performance in top-k recommendation rankings due to varying item payoffs. method Proposes a risk-seeking utility function for ranking items based on estimated preference scores.
result Risk-seeking ranking yields the best performance in top-k recommendations. A new method samples sequences without replacement using Gumbel-Top-k trick.
problem Sampling sequences without replacement from large domains efficiently.
method Gumbel-Top-k trick applied to Stochastic Beam Search.
result Efficient sampling with linear model evaluations in k. RAMPART ranks top-k features more accurately than existing methods.
problem Accurate ranking of important features in machine learning.
method Adaptive sequential halving strategy combined with ensembling techniques.
result RAMPART achieves the correct top-k ranking with high probability.
Proposes a method to infer ranking properties and top-K rankings with uncertainty quantification.
problem General uncertainty quantification in ranking problems.
method Combinatorial inference framework for the Bradley-Terry-Luce model, generalized to multiple testing.
result Minimax optimal method for inferring top-K rankings with FDR control.
Spectral method and regularized MLE are both optimal for top-K ranking from pairwise comparisons.
problem Identifying the top-K ranked items from pairwise comparisons.
method Adopting the Bradley-Terry-Luce model, the spectral method, and regularized MLE are used to estimate item scores and rank them.
result The spectral method and regularized MLE are minimax optimal in terms of sample complexity for top-K ranking.
New sparsity operator reduces variance reduction methods' computational cost.
problem Reduce computational cost of variance reduction methods.
method Introduce random-top-k operator to estimate gradient sparsity and reduce operations per update.
result Our algorithm consistently outperforms SpiderBoost in various tasks.
Interactive learning framework for various settings.
problem Various interactive learning settings.
method Adapted active learning algorithm for interactive structure discovery.
result Noise-tolerant algorithm with favorable query complexity.
Improves YouTube's recommendation system by correcting biases in logged feedback.
problem Data biases in logged feedback from multiple behavior policies.
method Top-K off-policy correction applied to REINFORCE algorithm.
result Efficacy demonstrated through simulations and live experiments.