Search Results for author:
Found 17 papers, 7 papers with code
Learning to Decode Collaboratively with Multiple Language Models
We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level.
Who Should Predict? Exact Algorithms For Learning to Defer to Humans
We show that prior approaches can fail to find a human-AI system with low misclassification error even when there exists a linear classifier and rejector that have zero error (the realizable setting).
TabLLM: Few-shot Classification of Tabular Data with Large Language Models
We study the application of large language models to zero-shot and few-shot classification of tabular data.
Training Subset Selection for Weak Supervision
Subset selection applies to any label model and classifier and is very simple to plug in to existing weak supervision pipelines, requiring just a few lines of code.
Large Language Models are Few-Shot Clinical Information Extractors
A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes.
Co-training Improves Prompt-based Learning for Large Language Models
We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data.
Leveraging Time Irreversibility with Order-Contrastive Pre-training
Label-scarce, high-dimensional domains such as healthcare present a challenge for modern machine learning techniques.
Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
We first present deep probabilistic logic(DPL), which offers a unifying framework for task-specific self-supervision by composing probabilistic logic with deep learning.
Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances
Several works have shown that perturbation stable instances of the MAP inference problem in Potts models can be solved exactly using a natural linear programming (LP) relaxation.
Self-supervised self-supervision by combining deep learning and probabilistic logic
Labeling training examples at scale is a perennial challenge in machine learning.
Graph cuts always find a global optimum for Potts models (with a catch)
On "real-world" instances, MAP assignments of small perturbations of the problem should be very similar to the MAP assignment(s) of the original problem instance.
Statistical Adaptive Stochastic Gradient Methods
We propose a statistical adaptive procedure called SALSA for automatically scheduling the learning rate (step size) in stochastic gradient methods.
Understanding the Role of Momentum in Stochastic Gradient Methods
The use of momentum in stochastic gradient methods has become a widespread practice in machine learning.
Statistical Adaptive Stochastic Optimization
We investigate statistical methods for automatically scheduling the learning rate (step size) in stochastic optimization.
Using Statistics to Automate Stochastic Optimization
Despite the development of numerous adaptive optimizers, tuning the learning rate of stochastic gradient methods remains a major roadblock to obtaining good practical performance in machine learning.
Block Stability for MAP Inference
The simplest stability condition assumes that the MAP solution does not change at all when some of the pairwise potentials are (adversarially) perturbed.
Optimality of Approximate Inference Algorithms on Stable Instances
Approximate algorithms for structured prediction problems---such as LP relaxations and the popular alpha-expansion algorithm (Boykov et al. 2001)---typically far exceed their theoretical performance guarantees on real-world instances.
