Search Results for author: Clara Fannjiang

Found 9 papers, 3 papers with code

Is novelty predictable?

no code implementations1 Jun 2023 Clara Fannjiang, Jennifer Listgarten

When designing objects to achieve novel property values with machine learning, one faces a fundamental challenge: how to push past the frontier of current knowledge, distilled from the training data into the model, in a manner that rationally controls the risk of failure.

Machine Learning for Protein Engineering

no code implementations26 May 2023 Kadina E. Johnston, Clara Fannjiang, Bruce J. Wittmann, Brian L. Hie, Kevin K. Yang, Zachary Wu

Directed evolution of proteins has been the most effective method for protein engineering.

Prediction-Powered Inference

2 code implementations23 Jan 2023 Anastasios N. Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I. Jordan, Tijana Zrnic

Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system.

Astronomy regression +1

Conformal prediction for the design problem

1 code implementation8 Feb 2022 Clara Fannjiang, Stephen Bates, Anastasios N. Angelopoulos, Jennifer Listgarten, Michael I. Jordan

This is challenging because of a characteristic type of distribution shift between the training and test data in the design setting -- one in which the training and test data are statistically dependent, as the latter is chosen based on the former.

Conformal Prediction Test

Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence

no code implementations30 Jun 2021 Ghassen Jerfel, Serena Wang, Clara Fannjiang, Katherine A. Heller, Yian Ma, Michael I. Jordan

We thus propose a novel combination of optimization and sampling techniques for approximate Bayesian inference by constructing an IS proposal distribution through the minimization of a forward KL (FKL) divergence.

Bayesian Inference Variational Inference

Autofocused oracles for model-based design

1 code implementation NeurIPS 2020 Clara Fannjiang, Jennifer Listgarten

The design goal is to construct an object with desired properties, such as a protein that binds to a therapeutic target, or a superconducting material with a higher critical temperature than previously observed.

regression

A view of Estimation of Distribution Algorithms through the lens of Expectation-Maximization

no code implementations24 May 2019 David H. Brookes, Akosua Busia, Clara Fannjiang, Kevin Murphy, Jennifer Listgarten

We show that a large class of Estimation of Distribution Algorithms, including, but not limited to, Covariance Matrix Adaption, can be written as a Monte Carlo Expectation-Maximization algorithm, and as exact EM in the limit of infinite samples.

Stochastic Optimization

Hallucinations in Neural Machine Translation

no code implementations27 Sep 2018 Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, David Sussillo

Neural machine translation (NMT) systems have reached state of the art performance in translating text and are in wide deployment.

Data Augmentation Hallucination +3

Cannot find the paper you are looking for? You can Submit a new open access paper.