b'Sanmi Koyejo'

research

∙ 07/20/2023

Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting

Language models can be prompted to reason through problems in a manner t...

0 Rylan Schaeffer, et al. ∙

research

∙ 07/20/2023

Deceptive Alignment Monitoring

As the capabilities of large machine learning models continue to grow, a...

0 Andres Carranza, et al. ∙

research

∙ 07/20/2023

FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation

We present FACADE, a novel probabilistic and geometric framework designe...

0 Dhruv Pai, et al. ∙

research

∙ 06/24/2023

Is Pre-training Truly Better Than Meta-Learning?

In the context of few-shot learning, it is currently believed that a fix...

0 Brando Miranda, et al. ∙

research

∙ 06/24/2023

Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data

Current trends to pre-train capable Large Language Models (LLMs) mostly ...

0 Alycia Lee, et al. ∙

research

∙ 06/22/2023

Communication-Efficient Federated Learning through Importance Sampling

The high communication cost of sending model updates from the clients to...

0 Berivan Isik, et al. ∙

research

∙ 06/20/2023

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Generative Pre-trained Transformer (GPT) models have exhibited exciting ...

0 Boxin Wang, et al. ∙

research

∙ 06/01/2023

Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions

We study the design of loss functions for click-through rates (CTR) to o...

0 Boxiang Lyu, et al. ∙

research

∙ 04/28/2023

Are Emergent Abilities of Large Language Models a Mirage?

Recent work claims that large language models display emergent abilities...

0 Rylan Schaeffer, et al. ∙

research

∙ 04/05/2023

Globalizing Fairness Attributes in Machine Learning: A Case Study on Health in Africa

With growing machine learning (ML) applications in healthcare, there hav...

0 Mercy Nyamewaa Asiedu, et al. ∙

research

∙ 03/01/2023

Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation

Nash Q-learning may be considered one of the first and most known algori...

0 Pedro Cisneros-Velarde, et al. ∙

research

∙ 12/21/2022

Adapting to Latent Subgroup Shifts via Concepts and Proxies

We address the problem of unsupervised domain adaptation when the source...

1 Ibrahim Alabdulmohsin, et al. ∙

research

∙ 10/04/2022

Invariant Aggregator for Defending Federated Backdoor Attacks

Federated learning is gaining popularity as it enables training of high-...

0 Xiaoyang Wang, et al. ∙

research

∙ 10/04/2022

Coordinated Science Laboratory 70th Anniversary Symposium: The Future of Computing

In 2021, the Coordinated Science Laboratory CSL, an Interdisciplinary Re...

0 Klara Nahrstedt, et al. ∙

research

∙ 08/02/2022

The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence

Recently, it has been observed that a transfer learning solution might b...

0 Brando Miranda, et al. ∙

research

∙ 05/31/2022

One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning

While parallelism has been extensively used in Reinforcement Learning (R...

0 Pedro Cisneros-Velarde, et al. ∙

research

∙ 05/01/2022

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction

More and more investors and machine learning models rely on social media...

3 Yong Xie, et al. ∙

research

∙ 01/31/2022

Fair Wrapping for Black-box Predictions

We introduce a new family of techniques to post-process ("wrap") a black...

2 Alexander Soen, et al. ∙

research

∙ 12/24/2021

Does MAML Only Work via Feature Re-use? A Data Centric Perspective

Recent work has suggested that a good embedding is all we need to solve ...

0 Brando Miranda, et al. ∙

research

∙ 12/24/2021

The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence

Recently, it has been observed that a transfer learning solution might b...

0 Brando Miranda, et al. ∙

research

∙ 07/10/2020

EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision

Deep generative models have enabled the automated synthesis of high-qual...

0 Siddharth Biswal, et al. ∙

research

∙ 06/24/2020

Fairness with Overlapping Groups

In algorithmically fair prediction problems, a standard goal is to ensur...

0 Forest Yang, et al. ∙

research

∙ 12/10/2019

Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients...

33 Peter Kairouz, et al. ∙

research

∙ 07/13/2019

FMRI data augmentation via synthesis

We present an empirical evaluation of fMRI data augmentation via synthes...

0 Peiye Zhuang, et al. ∙

research

∙ 04/11/2019

Max-Sliced Wasserstein Distance and its use for GANs

Generative adversarial nets (GANs) and variational auto-encoders have si...

12 Ishan Deshpande, et al. ∙

research

∙ 03/16/2019

SLSGD: Secure and Efficient Distributed On-device Machine Learning

We consider distributed on-device learning with limited communication an...

0 Cong Xie, et al. ∙

research

∙ 03/16/2019

Practical Distributed Learning: Secure Machine Learning with Communication-Efficient Local Updates

Federated learning on edge devices poses new challenges arising from wor...

0 Cong Xie, et al. ∙

research

∙ 03/10/2019

Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation

Recently, new defense techniques have been developed to tolerate Byzanti...

0 Cong Xie, et al. ∙

research

∙ 03/10/2019

Asynchronous Federated Optimization

Federated learning enables training on a massive number of edge devices....

0 Cong Xie, et al. ∙

research

∙ 01/30/2019

On the Consistency of Top-k Surrogate Losses

The top-k error is often employed to evaluate performance for challengin...

0 Forest Yang, et al. ∙

research

∙ 09/01/2018

A Contextual-bandit-based Approach for Informed Decision-making in Clinical Trials

Clinical trials involving multiple treatments utilize randomization of t...

0 Yogatheesan Varatharajah, et al. ∙

Sanmi Koyejo

Featured Co-authors