research
∙
08/28/2023
Goodhart's Law Applies to NLP's Explanation Benchmarks
Despite the rising popularity of saliency-based explanations, the resear...
share
research
∙
07/18/2023
Can Neural Network Memorization Be Localized?
Recent efforts at explaining the interplay of memorization and generaliz...
research
∙
07/06/2023
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Large web-sourced multimodal datasets have powered a slew of new methods...
research
∙
05/27/2023
Moral Machine or Tyranny of the Majority?
With Artificial Intelligence systems increasingly applied in consequenti...
research
∙
05/24/2023
PromptNER: Prompting For Named Entity Recognition
In a surprising turn, Large Language Models (LLMs) together with a growi...
research
∙
05/23/2023
USB: A Unified Summarization Benchmark Across Tasks and Domains
An abundance of datasets exist for training and evaluating models on the...
research
∙
05/22/2023
Evaluating Model Performance in Medical Datasets Over Time
Machine learning (ML) models deployed in healthcare systems must face da...
research
∙
05/08/2023
Risk-limiting Financial Audits via Weighted Sampling without Replacement
We introduce the notion of a risk-limiting financial auditing (RLFA): gi...
research
∙
04/16/2023
A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits
Personalized recommender systems suffuse modern life, shaping what media...
research
∙
03/13/2023
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
In recent years, NLP practitioners have converged on the following pract...
research
∙
03/09/2023
Users are the North Star for AI Transparency
Despite widespread calls for transparent artificial intelligence systems...
research
∙
02/16/2023
Local Causal Discovery for Estimating Causal Effects
Even when the causal graph underlying our data is unknown, we can use ob...
research
∙
02/06/2023
RLSbench: Domain Adaptation Under Relaxed Label Shift
Despite the emergence of principled methods for domain adaptation under ...
research
∙
02/06/2023
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
Open vocabulary models (e.g. CLIP) have shown strong performance on zero...
research
∙
01/27/2023
Meta-Learning Mini-Batch Risk Functionals
Supervised learning typically optimizes the expected value risk function...
research
∙
11/29/2022
Disentangling the Mechanisms Behind Implicit Regularization in SGD
A number of competing hypotheses have been proposed to explain why small...
research
∙
11/14/2022
Model Evaluation in Medical Datasets Over Time
Machine learning models deployed in healthcare systems face data drawn f...
research
∙
11/03/2022
Domain Adaptation under Missingness Shift
Rates of missing data often depend on record-keeping policies and thus m...
research
∙
10/26/2022
Characterizing Datapoints via Second-Split Forgetting
Researchers investigating example hardness have increasingly focused on ...
research
∙
10/21/2022
Neural Network Approximations of PDEs Beyond Linearity: Representational Perspective
A burgeoning line of research has developed deep neural networks capable...
research
∙
10/04/2022
Data drift correction via time-varying importance weight estimator
Real-world deployment of machine learning models is challenging when dat...
research
∙
09/28/2022
Downstream Datasets Make Surprisingly Good Pretraining Corpora
For most natural language processing tasks, the dominant practice is to ...
research
∙
09/14/2022
On the State of the Art in Authorship Attribution and Authorship Verification
Despite decades of research on authorship attribution (AA) and authorshi...
research
∙
08/28/2022
Learning Clinical Concepts for Predicting Risk of Progression to Severe COVID-19
With COVID-19 now pervasive, identification of high-risk individuals is ...
research
∙
07/26/2022
Unsupervised Learning under Latent Label Shift
What sorts of structure might enable a learner to discover classes from ...
research
∙
07/26/2022
Domain Adaptation under Open Set Label Shift
We introduce the problem of domain adaptation under Open Set Label Shift...
research
∙
06/27/2022
Supervised Learning with General Risk Functionals
Standard uniform convergence results bound the generalization gap of the...
research
∙
06/21/2022
On the Maximum Hessian Eigenvalue and Generalization
The mechanisms by which certain training interventions, such as increasi...
research
∙
06/08/2022
Resolving the Human Subjects Status of Machine Learning's Crowdworkers
In recent years, machine learning (ML) has come to rely more heavily on ...
research
∙
02/02/2022
Can Transformers be Strong Treatment Effect Estimators?
In this paper, we develop a general framework based on the Transformer a...
research
∙
01/11/2022
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Real-world machine learning deployments are characterized by mismatches ...
research
∙
12/17/2021
Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
In attempts to "explain" predictions of machine learning models, researc...
research
∙
11/01/2021
Mixture Proportion Estimation and PU Learning: A Modern Approach
Given only positive examples and unlabeled examples (from both positive ...
research
∙
10/14/2021
Practical Benefits of Feature Feedback Under Distribution Shift
In attempts to develop sample-efficient algorithms, researcher have expl...
research
∙
09/10/2021
Does Pretraining for Summarization Require Knowledge Transfer?
Pretraining techniques leveraging enormous datasets have driven recent a...
research
∙
08/20/2021
Efficient Online Estimation of Causal Effects by Deciding What to Observe
Researchers often face data fusion problems, where multiple data sources...
research
∙
07/01/2021
When Curation Becomes Creation: Algorithms, Microcontent, and the Vanishing Distinction between Platforms and Creators
Ever since social activity on the Internet began migrating from the wild...
research
∙
06/21/2021
Dive into Deep Learning
This open-source book represents our attempt to make deep learning appro...
research
∙
06/13/2021
Correcting Exposure Bias for Link Recommendation
Link prediction methods are frequently applied in recommender systems, e...
research
∙
06/02/2021
On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study
In adversarial data collection (ADC), a human workforce interacts with a...
research
∙
05/01/2021
RATT: Leveraging Unlabeled Data to Guarantee Generalization
To assess generalization, machine learning scientists typically either (...
research
∙
04/18/2021
Off-Policy Risk Assessment in Contextual Bandits
To evaluate prospective contextual bandit policies when experimentation ...
research
∙
03/04/2021
On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk
In order to model risk aversion in reinforcement learning, an emerging l...
research
∙
03/03/2021
Parametric Complexity Bounds for Approximating PDEs with Neural Networks
Recent empirical results show that deep networks can approximate solutio...
research
∙
02/20/2021
On Proximal Policy Optimization's Heavy-tailed Gradients
Modern policy gradient algorithms, notably Proximal Policy Optimization ...
research
∙
12/09/2020
Unpacking the Drop in COVID-19 Case Fatality Rates: A Study of National and Florida Line-Level Data
Since the COVID-19 pandemic first reached the United States, the case fa...
research
∙
12/01/2020
Evaluating Explanations: How much do explanations from the teacher aid students?
While many methods purport to explain predictions by highlighting salien...
research
∙
11/26/2020
Decoding and Diversity in Machine Translation
Neural Machine Translation (NMT) systems are typically evaluated using a...
research
∙
11/13/2020
Rebounding Bandits for Modeling Satiation Effects
Psychological research shows that enjoyment of many goods is subject to ...
research
∙
11/07/2020