research
∙
05/29/2023
Do Language Models Know When They're Hallucinating References?
Current state-of-the-art language models (LMs) are notorious for generat...
share
research
∙
04/19/2023
Loss minimization yields multicalibration for large neural networks
Multicalibration is a notion of fairness that aims to provide accurate p...
research
∙
11/20/2022
A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
Recent years have seen breakthroughs in neural language models that capt...
research
∙
09/01/2022
Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms
Neural Networks (NNs) struggle to efficiently learn certain problems, su...
research
∙
08/25/2022
Partial Matrix Completion
In the matrix completion problem, one wishes to reconstruct a low-rank m...
research
∙
08/18/2022
Using Large Language Models to Simulate Multiple Humans
We propose a method for using a large language model, such as GPT-3, to ...
research
∙
07/29/2022
Language Models Can Teach Themselves to Program Better
This work shows how one can use large-scale language models (LMs) to syn...
research
∙
05/19/2022
Why GANs are overkill for NLP
This work offers a novel theoretical perspective on why, despite numerou...
research
∙
09/11/2021
Omnipredictors
Loss minimization is a dominant paradigm in machine learning, where a pr...
research
∙
08/25/2021
Social Norm Bias: Residual Harms of Fairness-Aware Algorithms
Many modern learning algorithms mitigate bias by enforcing fairness acro...
research
∙
05/28/2021
Towards optimally abstaining from prediction
A common challenge across all areas of machine learning is that training...
research
∙
07/10/2020
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples
We present a transductive learning algorithm that takes as input trainin...
research
∙
10/04/2019
The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally
The long-term impact of algorithmic decision making is shaped by the dyn...
research
∙
04/26/2019
Learning to Prune: Speeding up Repeated Computations
It is common to encounter situations where one must solve a sequence of ...
research
∙
04/10/2019
What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
There is a growing body of work that proposes methods for mitigating bia...
research
∙
02/08/2019
Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
We study humor in Word Embeddings, a popular AI tool that associates eac...
research
∙
01/27/2019
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
We present a large-scale study of gender bias in occupation classificati...
research
∙
12/20/2018
What are the biases in my word embedding?
This paper presents an algorithm for enumerating biases in word embeddin...
research
∙
04/11/2018
Unleashing Linear Optimizers for Group-Fair Learning and Optimization
Most systems and learning algorithms optimize average performance or ave...
research
∙
04/11/2018
When optimizing nonlinear objectives is no harder than linear objectives
Most systems and learning algorithms optimize average performance or ave...
research
∙
12/11/2017
Usability of Humanly Computable Passwords
Reusing passwords across multiple websites is a common practice that com...
research
∙
09/25/2017
Glass-Box Program Synthesis: A Machine Learning Approach
Recently proposed models which learn to write computer programs from dat...
research
∙
12/29/2016
Meta-Unsupervised-Learning: A supervised approach to unsupervised learning
We introduce a new paradigm to investigate unsupervised learning, reduci...
research
∙
03/31/2015
Crowdsourcing Feature Discovery via Adaptively Chosen Comparisons
We introduce an unsupervised approach to efficiently discover the underl...
research
∙
09/17/2012
Textual Features for Programming by Example
In Programming by Example, a system attempts to infer a program from inp...
research
∙
04/11/2011