arXiv research

New SQ lower bounds show learning mixtures of bounded covariance Gaussians is hard.

We analyze computational limits of modern Hopfield models based on pattern norms.

This paper explores the computational hardness of generating latent vectors for generative models.

Fine-grained gap-dependent regret bounds for reinforcement learning.

Given a mixture between two populations of coins, "positive" coins that each have -- unknown and potentially different -- bias $\geq\frac{1}{2}+Δ$ and "negative" coins with bias $\leq\frac{1}{2}-Δ$, we consider the task of estimating the fraction $ρ$ of positive coins to within additive error $ε$. We achieve an upper a…

New algorithm reduces switching costs in multinomial logit bandit problems.

Improved Local SGD convergence for general convex objectives with bounded second-order heterogeneity.

New combinatorial dimension VCL refines learning curve theory.

New algorithm reduces regret in linear mixture SSPs without cost bounds.

Improved efficient robust regression with near-linear time and subquadratic samples.

Generative framework learns effective, lower-dimensional models from high-dimensional data.

Proposes a new method to generate unrestricted adversarial examples.

New algorithms reduce regret in both stochastic and deterministic environments.

Study on how many queries an adversary needs to make to match the best attack in white-box model.

UCRL-WVTR tackles long-term reinforcement learning with general approximations, achieving horizon-free and instance-dependent regret bounds.

NeuroDiff improves neural network equivalence verification with fine-grained approximations.

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that lea…

The thesis clarifies when local updates outperform centralized methods in heterogeneous data environments.

Fine-grained analysis of gradient descent with momentum provides modified loss equations.

Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism depending on the index representation scheme. As a result, fine-grained pruning ha…

As entity type systems become richer and more fine-grained, we expect the number of types assigned to a given entity to increase. However, most fine-grained typing work has focused on datasets that exhibit a low degree of type multiplicity. In this paper, we consider the high-multiplicity regime inherent in data source…

Bayes-UCBVI tackles reinforcement learning with a new upper confidence bound method.

New learner achieves optimal agnostic error in small error regime.

Paper presents UrbanFM and UrbanPy models for inferring fine-grained urban flows.

Study optimal and instance-dependent guarantees for solving linear equations with Markovian data.

Paper relaxes stability and generalization assumptions for SGD.

Considering event structure information has proven helpful in text-based stock movement prediction. However, existing works mainly adopt the coarse-grained events, which loses the specific semantic information of diverse event types. In this work, we propose to incorporate the fine-grained events in stock movement pred…

New analysis improves understanding of bilevel optimization stability and generalization.

Algorithm clusters mixtures with bounded covariances under specific separation conditions.

In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of weights of the DNNs, such as the Frobenius and spectral norms, and they are computed for weights grouped according to either input and outp…

FIGARO generates symbolic music with fine-grained control.

Study on DiTs' rates of approximation and estimation under various data assumptions.

DistPre predicts traffic speeds efficiently for large networks.

Fine-grained pretraining improves neural network's ability to learn rare features.

Paper addresses eigenvector perturbation in small eigen-gap scenarios.

ECN framework improves training on noisy structured labels.

Paper tackles bias-variance trade-off in missing data, proposing a dynamic framework.

Deep metric learning has been demonstrated to be highly effective in learning semantic representation and encoding information that can be used to measure data similarity, by relying on the embedding learned from metric learning. At the same time, variational autoencoder (VAE) has widely been used to approximate infere…

Sporting events are extremely complex and require a multitude of metrics to accurate describe the event. When making multiple predictions, one should make them from a single source to keep consistency across the predictions. We present a multi-task learning method of generating multiple predictions for analysis via a s…

Paper relaxes assumptions for non-parametric estimation in pairwise learning.

Efficient algorithms learn from coarse labels instead of fine grained ones.

We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual convolutional maps are turned on/off conditionally on features in the network. To achieve…

Obtaining accurate and well calibrated probability estimates from classifiers is useful in many applications, for example, when minimising the expected cost of classifications. Existing methods of calibrating probability estimates are applied globally, ignoring the potential for improvements by applying a more fine-gra…

This work generalizes transformer attention to capture higher-order correlations efficiently.

Proposes a method for weakly-supervised object localization to improve few-shot learning.

Proposes adaptive method for classifying interval-valued time series.

In construction projects, estimation of the settlement of fine-grained soils is of critical importance, and yet is a challenging task. The coefficient of consolidation for the compression index (Cc) is a key parameter in modeling the settlement of fine-grained soil layers. However, the estimation of this parameter is c…

We propose a probabilistic model for refining coarse-grained spatial data by utilizing auxiliary spatial data sets. Existing methods require that the spatial granularities of the auxiliary data sets are the same as the desired granularity of target data. The proposed model can effectively make use of auxiliary data set…