Page 2 of 4 for Machine Learning Posts - Page 2

BanditPAM: Almost Linear-Time k-medoids Clustering via Multi-Armed Bandits

We present an almost-linear time algorithm for the k-medoids problem that matches prior SOTA in clustering quality. Our solution has almost the same complexity as k-means and several advantages.

Selective Classification Can Magnify Disparities Across Groups

Erik Jones

We show that selective classification, where models are allowed to abstain when they are uncertain, can fail to improve and even hurt accuracy over certain subpopulations of the data.

Break-It-Fix-It: Unsupervised Learning for Fixing Source Code Errors

Michihiro Yasunaga

How can we use machine learning to fix source code errors (e.g. in C, Python) for us? We introduce Break-It-Fix-It, a new unsupervised method to train code repair models.

Our Journey towards Data-Centric AI: A Retrospective

Christopher Ré and Karan Goel

A retrospective narrative from the Hazy research lab on our work in data-centric AI, and current efforts on engaging the broader machine learning community.

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Ajay Mandlekar

We conducted an extensive study of six offline learning algorithms for robot manipulation on five simulated and three real-world multi-stage manipulation tasks of varying complexity, and with datasets of varying quality. Our study analyzes the most critical challenges when learning from offline h...

Reasoning with Language Models and Knowledge Graphs for Question Answering

Michihiro Yasunaga

We introduce an end-to-end question answering model, QA-GNN, that jointly reasons with pre-trained language models and knowledge graphs.

Extrapolating to Unnatural Language Processing with GPT-3's In-context Learning: The Good, the Bad, and the Mysterious

Frieda Rong

In this post, we examine in-context learning in GPT-3 through a series of experiments dissecting GPT-3's ability to extrapolate to less natural inputs.

Neural Mechanics: Symmetry and Broken Conservation Laws In Deep Learning Dynamics

Daniel Kunin and Hidenori Tanaka

By exploiting architectural symmetry, our work demonstrates that we can analytically describe the learning dynamics of various parameter combinations at finite learning rates and batch sizes for state of the art architectures trained on any dataset.

Do Language Models Know How Heavy an Elephant Is?

Xikun Zhang

Humans have a pretty good sense of scale, like the weight or price of different objects, but do pre-trained language representations? We measure how well pre-trained text representations capture scale and also come up with a improved version of BERT that captures scale better.

Blue People v. City of Ney

Fereshte Khani

Discriminatory behavior towards certain groups by machine learning (ML) models is concerning in critical applications such as hiring. We show that when ML models use noisy features, they're incentivized to devalue a good score when the candidate is from a lower-performing group.