Search Results for author:
Found 14 papers, 7 papers with code
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design.
The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
Transformer-based Large Language Models (LLMs) have become a fixture in modern machine learning.
Streaming Active Learning with Deep Neural Networks
Active learning is perhaps most naturally posed as an online learning problem.
Neural Active Learning on Heteroskedastic Distributions
To this end, we demonstrate the catastrophic failure of these active learning algorithms on heteroskedastic distributions and propose a fine-tuning-based approach to mitigate these failures.
Eigen Memory Trees
This work introduces the Eigen Memory Tree (EMT), a novel online memory model for sequential learning scenarios.
Transformers Learn Shortcuts to Automata
Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine.
Anti-Concentrated Confidence Bonuses for Scalable Exploration
Intrinsic rewards play a central role in handling the exploration-exploitation trade-off when designing sequential decision-making algorithms, in both foundational theory and state-of-the-art deep reinforcement learning.
Investigating the Role of Negatives in Contrastive Representation Learning
We focus on disambiguating the role of one of these parameters: the number of negative examples.
Gone Fishing: Neural Active Learning with Fisher Embeddings
There is an increasing need for effective active learning algorithms that are compatible with deep neural networks.
Learning Composable Energy Surrogates for PDE Order Reduction
We use a neural network to model the stored potential energy in a component given boundary conditions.
On Warm-Starting Neural Network Training
We would like each of these models in the sequence to be performant and take advantage of all the data that are available to that point.
On The Difficulty of Warm-Starting Neural Network Training
We would like each of these models in the sequence to be performant and take advantage of all the data that are available to that point.
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
We design a new algorithm for batch active learning with deep neural network models.
Unsupervised Domain Adaptation Using Approximate Label Matching
Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution.
