Search Results for author:
Found 15 papers, 8 papers with code
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources.
Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale
We demonstrate that recent advances in reinforcement learning (RL) combined with simple architectural changes significantly improves generalization on the ProcGen benchmark.
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious due to the need for manually crafted prompts.
Understanding prompt engineering may not require rethinking generalization
Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive performance in many settings.
On the Joint Interaction of Models, Data, and Features
Thus, we believe this work provides valuable new insight into our understanding of feature learning.
Permutation Equivariant Neural Functionals
The key building blocks of this framework are NF-Layers (neural functional layers) that we constrain to be permutation equivariant through an appropriate parameter sharing scheme.
Learning Options via Compression
Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks.
Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift
In this paper, we show a similar but surprising phenomenon also holds for the agreement between pairs of neural network classifiers: whenever accuracy-on-the-line holds, we observe that the OOD agreement between the predictions of any two pairs of neural networks (with potentially different architectures) also observes a strong linear correlation with their ID agreement.
Assessing Generalization of SGD via Disagreement
We empirically show that the test error of deep networks can be estimated by simply training the same architecture on the same training set but with a different run of Stochastic Gradient Descent (SGD), and measuring the disagreement rate between the two networks on unlabeled test data.
Ask & Explore: Grounded Question Answering for Curiosity-Driven Exploration
In many real-world scenarios where extrinsic rewards to the agent are extremely sparse, curiosity has emerged as a useful concept providing intrinsic rewards that enable the agent to explore its environment and acquire information to achieve its goals.
NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
Understanding generalization in deep learning is arguably one of the most important questions in deep learning.
Observational Overfitting in Reinforcement Learning
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process (MDP).
Fantastic Generalization Measures and Where to Find Them
We present the first large scale study of generalization in deep networks.
Language as an Abstraction for Hierarchical Deep Reinforcement Learning
We find that, using our approach, agents can learn to solve to diverse, temporally-extended tasks such as object sorting and multi-object rearrangement, including from raw pixel observations.
Predicting the Generalization Gap in Deep Networks with Margin Distributions
In this paper, we propose such a measure, and conduct extensive empirical studies on how well it can predict the generalization gap.
