Search Results for author: Yiding Jiang

Found 14 papers, 8 papers with code

Language models are weak learners

no code implementations25 Jun 2023 Hariharan Manikandan, Yiding Jiang, J Zico Kolter

Specifically, we illustrate the use of a large language model (LLM) as a weak learner in a boosting algorithm applied to tabular data.

Few-Shot Learning Language Modelling +1

On the Importance of Exploration for Generalization in Reinforcement Learning

1 code implementation8 Jun 2023 Yiding Jiang, J. Zico Kolter, Roberta Raileanu

Existing approaches for improving generalization in deep reinforcement learning (RL) have mostly focused on representation learning, neglecting RL-specific aspects such as exploration.

Decision Making reinforcement-learning +2

On the Joint Interaction of Models, Data, and Features

no code implementations7 Jun 2023 Yiding Jiang, Christina Baek, J. Zico Kolter

Thus, we believe this work provides valuable new insight into our understanding of feature learning.

Neural Functional Transformers

1 code implementation22 May 2023 Allan Zhou, KaiEn Yang, Yiding Jiang, Kaylee Burns, Winnie Xu, Samuel Sokota, J. Zico Kolter, Chelsea Finn

The recent success of neural networks as implicit representation of data has driven growing interest in neural functionals: models that can process other neural networks as input by operating directly over their weight spaces.

Permutation Equivariant Neural Functionals

1 code implementation27 Feb 2023 Allan Zhou, KaiEn Yang, Kaylee Burns, Yiding Jiang, Samuel Sokota, J. Zico Kolter, Chelsea Finn

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.

Inductive Bias

Learning Options via Compression

1 code implementation8 Dec 2022 Yiding Jiang, Evan Zheran Liu, Benjamin Eysenbach, Zico Kolter, Chelsea Finn

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

1 code implementation27 Jun 2022 Christina Baek, Yiding Jiang, aditi raghunathan, Zico Kolter

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.

Model Selection

Assessing Generalization of SGD via Disagreement

no code implementations ICLR 2022 Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter

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

no code implementations24 Apr 2021 Jivat Neet Kaur, Yiding Jiang, Paul Pu Liang

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.

Question Answering

Observational Overfitting in Reinforcement Learning

no code implementations ICLR 2020 Xingyou Song, Yiding Jiang, Stephen Tu, Yilun Du, Behnam Neyshabur

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).

reinforcement-learning Reinforcement Learning (RL)

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

2 code implementations NeurIPS 2019 Yiding Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn

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.

Instruction Following reinforcement-learning +1

Predicting the Generalization Gap in Deep Networks with Margin Distributions

2 code implementations ICLR 2019 Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio

In this paper, we propose such a measure, and conduct extensive empirical studies on how well it can predict the generalization gap.

Cannot find the paper you are looking for? You can Submit a new open access paper.