Search Results for author:
Found 12 papers, 1 papers with code
Positive Semidefinite Supermartingales and Randomized Matrix Concentration Inequalities
We present new concentration inequalities for either martingale dependent or exchangeable random symmetric matrices under a variety of tail conditions, encompassing now-standard Chernoff bounds to self-normalized heavy-tailed settings.
Time-Uniform Confidence Spheres for Means of Random Vectors
We derive and study time-uniform confidence spheres -- confidence sphere sequences (CSSs) -- which contain the mean of random vectors with high probability simultaneously across all sample sizes.
Anytime-valid t-tests and confidence sequences for Gaussian means with unknown variance
These are respectively obtained by swapping Lai's flat mixture for a Gaussian mixture, and swapping the right Haar mixture over $\sigma$ with the maximum likelihood estimate under the null, as done in universal inference.
Dynamic Visual Prompt Tuning for Parameter Efficient Transfer Learning
Parameter efficient transfer learning (PETL) is an emerging research spot that aims to adapt large-scale pre-trained models to downstream tasks.
The extended Ville's inequality for nonintegrable nonnegative supermartingales
Following the initial work by Robbins, we rigorously present an extended theory of nonnegative supermartingales, requiring neither integrability nor finiteness.
Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution
In addition, we collect a real-world dataset with spatially aligned events and RGB frames.
A unified recipe for deriving (time-uniform) PAC-Bayes bounds
We present a unified framework for deriving PAC-Bayesian generalization bounds.
Huber-Robust Confidence Sequences
Confidence sequences are confidence intervals that can be sequentially tracked, and are valid at arbitrary data-dependent stopping times.
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
In this paper, we provide convergence guarantees for SGD under a state-dependent and heavy-tailed noise with a potentially infinite variance, for a class of strongly convex objectives.
Automatic Historical Feature Generation through Tree-based Method in Ads Prediction
Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads.
Targeted Source Detection for Environmental Data
In the face of growing needs for water and energy, a fundamental understanding of the environmental impacts of human activities becomes critical for managing water and energy resources, remedying water pollution, and making regulatory policy wisely.
A Simple Baseline for Travel Time Estimation using Large-Scale Trip Data
The increased availability of large-scale trajectory data around the world provides rich information for the study of urban dynamics.
