arXiv research

Paper tackles hypothesis transfer learning for black-box models.

LADaR framework calibrates machine learning models for instance-wise predictions.

In the Best-$k$-Arm problem, we are given $n$ stochastic bandit arms, each associated with an unknown reward distribution. We are required to identify the $k$ arms with the largest means by taking as few samples as possible. In this paper, we make progress towards a complete characterization of the instance-wise sample…

The paper formalizes feature attribution to address inconsistent definitions and evaluate methods.

Understanding black-box machine learning models is crucial for their widespread adoption. Learning globally interpretable models is one approach, but achieving high performance with them is challenging. An alternative approach is to explain individual predictions using locally interpretable models. For locally interpre…

nFBST tests neural networks using Bayesian methods.

GL-LowPopArt improves minimax-optimal estimation for trace regression.

SoftCLT improves time series representation learning by soft contrastive loss.

ISAHP discovers instance-level causal structures in event sequences.

New method calibrates neural network predictions for better reliability.

We consider the thresholding bandit problem, whose goal is to find arms of mean rewards above a given threshold $θ$, with a fixed budget of $T$ trials. We introduce LSA, a new, simple and anytime algorithm that aims to minimize the aggregate regret (or the expected number of mis-classified arms). We prove that our algo…

Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on node-wise classification, illustrated with community detection on stochastic block m…

Proposes MEED framework for model interpretation.

New method selects features for sequential decision making.

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

A new algorithm reduces regret in bandit problems with adversarial corruptions.

Many machine learning tasks require sampling a subset of items from a collection based on a parameterized distribution. The Gumbel-softmax trick can be used to sample a single item, and allows for low-variance reparameterized gradients with respect to the parameters of the underlying distribution. However, stochastic o…

FIT evaluates time series model feature importance quantifying distributional shift.

Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably sensitive to factors unrelated to the model's decision making process. We instead propo…

PiNets provide faithful explanations for neural networks.

SuNCEt accelerates contrastive learning with minimal labeled data.

Paper develops efficient mechanisms for estimating variance and covariance under differential privacy in the add-remove model.

Survey on assessing and improving classifier calibration for better decision making.

Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and challenging for machines. We introduce a new approach to facilitate the discovery…

Last SGD iterate bounds for overparameterized linear regression.

This research improves deep neural network calibration using a new loss function.

GD outperforms ridge regression and SGD in linear regression problems.

Simple method for estimating missing panel data entries with confidence intervals.

MET learns tabular data representations without data augmentations.

The paper offers a method to create prediction sets with uncertainty control.

This paper analyzes multi-pass SGD for least squares, improving generalization bounds.

Paper proposes a method to train robust neural networks without labeled data.

Efficiently refits black box predictions with wild refitting method.

A new recursive mixture estimation algorithm improves VAE inference efficiency and accuracy.

In this paper, we propose an extension to an existing algorithm (instance-MIR) which tackles the multiple instance regression (MIR) problem, also known as distribution regression. The MIR setting arises when the data is a collection of bags, where each bag consists of several instances which correspond to the same and …

New method solves matrix completion problems to certifiable optimality.

Paper analyzes GLM-tron for high-dimensional ReLU regression, providing upper and lower bounds.

Paper tackles cross-granularity few-shot learning with meta-embedder.

Improved algorithm for logistic bandits with better regret bounds.

We study the combinatorial pure exploration problem Best-Set in stochastic multi-armed bandits. In a Best-Set instance, we are given $n$ arms with unknown reward distributions, as well as a family $\mathcal{F}$ of feasible subsets over the arms. Our goal is to identify the feasible subset in $\mathcal{F}$ with the maxi…

Discovering imaging biomarkers for autism spectrum disorder (ASD) is critical to help explain ASD and predict or monitor treatment outcomes. Toward this end, deep learning classifiers have recently been used for identifying ASD from functional magnetic resonance imaging (fMRI) with higher accuracy than traditional lear…

In the classical best arm identification (Best-$1$-Arm) problem, we are given $n$ stochastic bandit arms, each associated with a reward distribution with an unknown mean. We would like to identify the arm with the largest mean with probability at least $1-δ$, using as few samples as possible. Understanding the sample c…

A new weighted MCC measure improves classifier performance evaluation.

Stability of weighted extremal manifolds proven through blowups.

Develops theory of weightings for Lie groupoids and algebroids.

The paper extends spin geometry to weighted manifolds and defines a new mass for Ricci flow.

The study explores weightings on submanifolds and their geometric properties.

New mass and staticity concepts derived from weighted curvature maps.