Top/O's first two k-invariants are zero.
problem Understanding the structure of Top/O.
method Analyzing the first two k-invariants.
result The first two k-invariants of Top/O vanish.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Top Two”
New algorithm reduces sample complexity for Top Two method.
problem Fixed-confidence best arm identification for Top Two methods.
method UCB-based Top Two algorithm for non-asymptotic analysis.
result First non-asymptotic upper bound on expected sample complexity.
Top-two algorithm improved for best-k-arm selection.
problem Best-k-arm identification in multi-armed bandits.
method Information-directed selection based on dual variables.
result Top-two Thompson sampling with IDS is asymptotically optimal.
Top Two Algorithms Revisitedstat.ML
Improved theoretical guarantees for Top Two algorithms.
problem Theoretical support for best arm identification with bounded distributions.
method General analysis of Top Two methods, identifying desirable properties and replacing sampling step.
result Theoretical support for Top Two algorithms with bounded distributions.
Paper recovers top-two answers and confusion probability in multi-choice crowdsourcing.
problem Recovering top-two answers and confusion probability in multi-choice crowdsourcing tasks.
method Proposes a two-stage inference algorithm based on a model quantifying task difficulty and worker reliability.
result Achieves minimax optimal convergence rate and outperforms other algorithms in synthetic and real data experiments.
We propose Top-N-Rank, a novel family of list-wise Learning-to-Rank models for reliably recommending the N top-ranked items. The proposed models optimize a variant of the widely used discounted cumulative gain (DCG) objective function which differs from DCG in two important aspects: (i) It limits the evaluation of DCG …
This paper studies the problem of identifying any distinct arms among the top fraction (e.g., top 5\%) of arms from a finite or infinite set with a probably approximately correct (PAC) tolerance . We consider two cases: (i) when the threshold of the top arms' expected rewards is known and (ii) when it is unk…
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- Learning-to-Defer framework, including adaptive Top- variant.
result Superior accuracy-cost trade-offs with multi-expert deferral.
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.
We have recently introduced the ``thermal optimal path'' (TOP) method to investigate the real-time lead-lag structure between two time series. The TOP method consists in searching for a robust noise-averaged optimal path of the distance matrix along which the two time series have the greatest similarity. Here, we gener…
Bottom-up algorithms outperform top-down in hierarchical community detection at intermediate levels.
problem Finding the optimal hierarchical community structure in networks.
method A bottom-up algorithm for hierarchical clustering of networks.
result Bottom-up algorithms achieve the information-theoretic threshold for exact recovery at intermediate levels of the hierarchy.
Let be a two-periodic braid and let be its quotient. In this paper we show there is a spectral sequence from the next-to-top winding number grading of the sutured annular Khovanov homology of the closure of to the next-to-top winding number grading of the sutured annular Khovanov hom…
We study the top- ranking problem where the goal is to recover the set of top- 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…
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classificationcs.CV
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…
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.
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…
Top-H decoding improves text generation by balancing creativity and coherence.
problem Balancing creativity and coherence in text generation.
method Entropy-constrained minimum divergence problem, NP-hard ECMM problem, top-H decoding.
result Top-H decoding outperforms min-p sampling by up to 25.63% on creative writing benchmarks.
DeepTopPush improves accuracy at the top for complex classification tasks.
problem Minimizing irrelevant samples above a threshold in binary classification.
method Proposes a new method for end-to-end training of deep networks to minimize loss at the top.
result Demonstrates excellent performance on visual recognition and real-world applications.
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.
Suppose is a connected complex Lie group and is a discrete subgroup such that is Kähler and the codimension of the top non--vanishing homology group of with coefficients in is less than or equal to two. We show that is solvable and a finite covering of is biholomorphic to a …
Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that , , or algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on predi…
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.
The paper reveals a spinning top geometry in real-world games.
problem Understanding the structure of real-world games.
method Developed a spinning top geometric model and used Nash clustering.
result Real-world games exhibit a spinning top structure with transitive and non-transitive dimensions.
Two graph homologies help compute embedding space.
problem Computing the rational homotopy group of long embeddings.
method Invented two graph homologies and constructed a map between them.
result A monomorphism from top hairy graph homology to top BCR graph homology.
Efficient unsupervised training and inference in deep generative models remains a challenging problem. One basic approach, called Helmholtz machine, involves training a top-down directed generative model together with a bottom-up auxiliary model used for approximate inference. Recent results indicate that better genera…
A new KD model for collaborative filtering improves top-N recommendation performance.
problem Challenges in applying KD to recommender models due to feedback sparsity and ambiguity.
method Proposes a new KD model (CD) for collaborative filtering, reformulating a loss function, using probabilistic rank-aware sampling, and developing training strategies.
result Outperforms state-of-the-art methods by 2.7-33.2% in hit rate (HR) and 2.7-29.1% in NDCG.
The paper finds conical higher cscK metrics on minimal ruled surfaces with conical singularities.
problem Existence of conical higher cscK metrics on minimal ruled surfaces.
method Develop conical singularities along at least one of the two special divisors and use the momentum construction.
result Conical higher cscK metrics exist in each Kähler class on minimal ruled surfaces.
New methods provide stable ranking without assumptions on data distributions.
problem Stability issues in ranking problems with noisy data.
method Developed a stability framework and two ranking operators.
result Guaranteed stability without assumptions on data distributions.
We consider a situation in which we see samples in drawn i.i.d. from some distribution with mean zero and unknown covariance A. We wish to compute the top eigenvector of A in an incremental fashion - with an algorithm that maintains an estimate of the top eigenvector in O(d) space, and incrementally adju…
Top-k Multiclass SVMstat.ML
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- 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- classification. Surprisingly, it is not rigorously und…
We explore the top- 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- ranked items based on partially revealed preference information. We investigate the Bradley-Terry-Luce model in which one ranks items ac…
Classical dynamical equations describing a certain version of the nonHamiltonian interaction of two rotators (Euler tops with completely degenerate inertia tensors) are considered. The simplest case is integrated. It is shown that the dynamics is almost periodic with periods depending on the initial data.
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.
We present the symmetric thermal optimal path (TOPS) method to determine the time-dependent lead-lag relationship between two stochastic time series. This novel version of the previously introduced TOP method alleviates some inconsistencies by imposing that the lead-lag relationship should be invariant with respect to …
New sampling rules improve best-arm identification in Bayesian bandits.
problem Best-arm identification in Bayesian bandits with fixed confidence guarantees.
method Top-Two Thompson Sampling (TTTS) and Top-Two Transportation Cost (T3C).
result First sample complexity analysis of TTTS and T3C for Gaussian rewards.
Optimal top-2 method improves best arm identification with reduced error.
problem Identifying the arm with the highest mean in a set of arms.
method A novel top-2 algorithm that pulls the empirical best arm with probability β and the challenger arm otherwise.
result The proposed algorithm matches the information theoretic lower bound on sample complexity as δ approaches 0.
Paper tackles non-identifiability of mixture models in partial order datasets.
problem Non-identifiability of mixture models in datasets with partial orders.
method Proved non-identifiability conditions and proposed GMM algorithms.
result GMM algorithms for learning mixtures of two Plackett-Luce models are consistent.
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- Learning-to-Defer framework with a convex surrogate.
result Unified model achieves superior accuracy-cost trade-offs.
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.
We study the active learning problem of top- ranking from multi-wise comparisons under the popular multinomial logit model. Our goal is to identify the top- 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…
Proposes top-label calibration and M2B framework for multiclass to binary calibration.
problem Multiclass calibration and interpretation issues.
method Top-label calibration and M2B reduction framework.
result M2B + HB achieves lower calibration error than other methods.
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…
Paper proves every stable 4-sphere has a unique diffeomorphism class.
problem Identifying stable 4-spheres and their diffeomorphisms.
method Using Wall's result and properties of surface-knot spaces.
result Every stable 4-sphere has a unique orientation-preserving diffeomorphism class.
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.
New findings on convexity of special Lagrangian geodesics.
problem Convexity of special Lagrangian geodesics in space-time.
method Space-time coordinate transformation preserving Lagrangian angle, leading to estimate.
result Subsolutions in all branches of the degenerate special Lagrangian equation are bi-convex.
In this paper, we introduce a geometric structure called top, which is a trivialized bundle of plane pencils over a Riemannian 3-manifold, defined as the set of kernels of a circle of 1-forms (e.g. of contact and integrable forms) with particular properties with respect to the metric. We classify the manifolds which ad…
Top-k Combinatorial Bandits generalize multi-armed bandits, where at each round any subset of out of 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…