Search Results for author:
Found 35 papers, 8 papers with code
Learning and Evaluating a Differentially Private Pre-trained Language Model
One method to guarantee the privacy of such individuals is to train a differentially-private language model, but this usually comes at the expense of model performance.
Health AI Developer Foundations
Finally, while HAI-DEF and specifically the foundation models lower the barrier to entry for ML in healthcare, we emphasize the importance of validation with problem- and population-specific data for each desired usage setting.
Can Few-shot Work in Long-Context? Recycling the Context to Generate Demonstrations
Despite recent advancements in Large Language Models (LLMs), their performance on tasks involving long contexts remains sub-optimal.
Multi-turn Reinforcement Learning from Preference Human Feedback
Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks.
The Temporal Structure of Language Processing in the Human Brain Corresponds to The Layered Hierarchy of Deep Language Models
Our results reveal a connection between human language processing and DLMs, with the DLM's layer-by-layer accumulation of contextual information mirroring the timing of neural activity in high-order language areas.
AI Increases Global Access to Reliable Flood Forecasts
Using AI, we achieve reliability in predicting extreme riverine events in ungauged watersheds at up to a 5-day lead time that is similar to or better than the reliability of nowcasts (0-day lead time) from a current state of the art global modeling system (the Copernicus Emergency Management Service Global Flood Awareness System).
Using generative AI to investigate medical imagery models and datasets
In this paper, we present a method for automatic visual explanations leveraging team-based expertise by generating hypotheses of what visual signals in the images are correlated with the task.
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input.
Abstractive Text Summarization
Natural Language Inference
+3
Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning
Despite recent advances in natural language understanding and generation, and decades of research on the development of conversational bots, building automated agents that can carry on rich open-ended conversations with humans "in the wild" remains a formidable challenge.
TRUE: Re-evaluating Factual Consistency Evaluation
Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability.
Flood forecasting with machine learning models in an operational framework
During the 2021 monsoon season, the flood warning system was operational in India and Bangladesh, covering flood-prone regions around rivers with a total area of 287, 000 km2, home to more than 350M people.
Adversarial Robustness of Streaming Algorithms through Importance Sampling
In this paper, we introduce adversarially robust streaming algorithms for central machine learning and algorithmic tasks, such as regression and clustering, as well as their more general counterparts, subspace embedding, low-rank approximation, and coreset construction.
Explaining in Style: Training a GAN to explain a classifier in StyleSpace
A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image.
ML-based Flood Forecasting: Advances in Scale, Accuracy and Reach
Floods are among the most common and deadly natural disasters in the world, and flood warning systems have been shown to be effective in reducing harm.
The Large Core of College Admission Markets: Theory and Evidence
In Hungary, where such heterogeneity is present, a non-merit-based stable allocation would increase the number of assigned applicants by 1. 9%, and affect 8. 3% of the applicants relative to any merit-based stable allocation.
An Optimal Elimination Algorithm for Learning a Best Arm
We consider the classic problem of $(\epsilon,\delta)$-PAC learning a best arm where the goal is to identify with confidence $1-\delta$ an arm whose mean is an $\epsilon$-approximation to that of the highest mean arm in a multi-armed bandit setting.
Adversarially Robust Streaming Algorithms via Differential Privacy
A streaming algorithm is said to be adversarially robust if its accuracy guarantees are maintained even when the data stream is chosen maliciously, by an adaptive adversary.
Spectral Algorithm for Low-rank Multitask Regression
In this scenario sharing a low-rank component between the tasks translates to a shared spectral reflection of the water, which is a true underlying physical model.
Personalizing ASR for Dysarthric and Accented Speech with Limited Data
In this paper, we present and evaluate finetuning techniques to improve ASR for users with non-standard speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Audio De-identification - a New Entity Recognition Task
To this end, we define the task of audio de-ID, in which audio spans with entity mentions should be detected.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
LSH Microbatches for Stochastic Gradients: Value in Rearrangement
We make a principled argument for the properties of our arrangements that accelerate the training and present efficient algorithms to generate microbatches that respect the marginal distribution of training examples.
Audio De-identification: A New Entity Recognition Task
To this end, we define the task of audio de-ID, in which audio spans with entity mentions should be detected.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Learning to Screen
(ii) In the second variant it is assumed that before the process starts, the algorithm has an access to a training set of $n$ items drawn independently from the same unknown distribution (e. g.\ data of candidates from previous recruitment seasons).
ML for Flood Forecasting at Scale
We propose to build on these strengths and develop ML systems for timely and accurate riverine flood prediction.
Towards Global Remote Discharge Estimation: Using the Few to Estimate The Many
We demonstrate the efficacy of our approach for the problem of discharge estimation using simulations.
Optimization for Approximate Submodularity
We consider the problem of maximizing a submodular function when given access to its approximate version.
Online Linear Quadratic Control
We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses.
Planning and Learning with Stochastic Action Sets
From an RL perspective, we show that Q-learning with sampled action sets is sound.
Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video.
Self-Similar Epochs: Value in Arrangement
Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples.
MUDA: A Truthful Multi-Unit Double-Auction Mechanism
In a seminal paper, McAfee (1992) presented a truthful mechanism for double auctions, attaining asymptotically-optimal gain-from-trade without any prior information on the valuations of the traders.
Computer Science and Game Theory
Robust Guarantees of Stochastic Greedy Algorithms
In this paper we analyze the robustness of stochastic variants of the greedy algorithm for submodular maximization.
Fair Allocation based on Diminishing Differences
We give a full characterization of allocations that are necessarily-proportional or possibly-proportional according to this assumption.
Computer Science and Game Theory
Submodular Optimization under Noise
We provide initial answers, by focusing on the question of maximizing a monotone submodular function under a cardinality constraint when given access to a noisy oracle of the function.
Quantum algorithm for solving linear systems of equations
Solving linear systems of equations is a common problem that arises both on its own and as a subroutine in more complex problems: given a matrix A and a vector b, find a vector x such that Ax=b.
Quantum Physics
