activity
20122024
most citedScore-Based Generative Modeling through Stochastic Differential Equations

1.3k citations · 2.3k across the 69 of their papers we have counts for

collaborators
Showing stat.MLShow all

18 papers · 1 filter

stat.ML20214 cited

Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration

Shengjia Zhao, Michael P. Kim, Roshni Sahoo +2

When facing uncertainty, decision-makers want predictions they can trust. A machine learning provider can convey confidence to decision-makers by guaranteeing their predictions are…

stat.ML2021

Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information

Willie Neiswanger, Ke Alexander Wang, Stefano Ermon

In many real-world problems, we want to infer some property of an expensive black-box function , given a budget of function evaluations. One example is budget constrained gl…

stat.ML2021

Maximum Likelihood Training of Score-Based Diffusion Models

Yang Song, Conor Durkan, Iain Murray +1

Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matchin…

stat.ML2020

Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration

Shengjia Zhao, Stefano Ermon

Decision makers often need to rely on imperfect probabilistic forecasts. While average performance metrics are typically available, it is difficult to assess the quality of individ…

stat.ML2020

A Framework for Sample Efficient Interval Estimation with Control Variates

Shengjia Zhao, Christopher Yeh, Stefano Ermon

We consider the problem of estimating confidence intervals for the mean of a random variable, where the goal is to produce the smallest possible interval for a given number of samp…

stat.ML202014 cited

Individual Calibration with Randomized Forecasting

Shengjia Zhao, Tengyu Ma, Stefano Ermon

Machine learning applications often require calibrated predictions, e.g. a 90\% credible interval should contain the true outcome 90\% of the times. However, typical definitions of…