Search Results for author:
Found 10 papers, 7 papers with code
What Makes Good In-Context Examples for GPT-3?
In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples (relative to random sampling) that better leverage GPT-3’s in-context learning capabilities. Inspired by the recent success of leveraging a retrieval module to augment neural networks, we propose to retrieve examples that are semantically-similar to a test query sample to formulate its corresponding prompt.
Fast and Interpretable Mortality Risk Scores for Critical Care Patients
Both of these have disadvantages: black box models are unacceptable for use in hospitals, whereas manual creation of models (including hand-tuning of logistic regression parameters) relies on humans to perform high-dimensional constrained optimization, which leads to a loss in performance.
Syntax Tree Constrained Graph Network for Visual Question Answering
Existing VQA methods integrate vision modeling and language understanding to explore the deep semantics of the question.
Causal Intervention for Abstractive Related Work Generation
Abstractive related work generation has attracted increasing attention in generating coherent related work that better helps readers grasp the background in the current research.
OKRidge: Scalable Optimal k-Sparse Ridge Regression
We consider an important problem in scientific discovery, namely identifying sparse governing equations for nonlinear dynamical systems.
Exploring and Interacting with the Set of Good Sparse Generalized Additive Models
In real applications, interaction between machine learning models and domain experts is critical; however, the classical machine learning paradigm that usually produces only a single model does not facilitate such interaction.
FasterRisk: Fast and Accurate Interpretable Risk Scores
Specifically, our approach produces a pool of almost-optimal sparse continuous solutions, each with a different support set, using a beam-search algorithm.
Fast Sparse Classification for Generalized Linear and Additive Models
For fast sparse logistic regression, our computational speed-up over other best-subset search techniques owes to linear and quadratic surrogate cuts for the logistic loss that allow us to efficiently screen features for elimination, as well as use of a priority queue that favors a more uniform exploration of features.
What Makes Good In-Context Examples for GPT-$3$?
Inspired by the recent success of leveraging a retrieval module to augment large-scale neural network models, we propose to retrieve examples that are semantically-similar to a test sample to formulate its corresponding prompt.
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
In this paper, we propose a novel Contrastive Log-ratio Upper Bound (CLUB) of mutual information.
