Jinwoo Shin

Adiabatic Persistent Contrastive Divergence Learning

2016 · arXiv (Cornell University)

This paper studies the problem of parameter learning in probabilistic graphical models having latent variables, where the standard approach is the expectation maximization algorithm alternating expectation (E) and maximization (M) steps. However, both E and …

Optimizing Spectral Sums using Randomized Chebyshev Expansions.

2018 · arXiv (Cornell University)

The trace of matrix functions, often called spectral sums, e.g., rank, log-determinant and nuclear norm, appear in many machine learning tasks. However, optimizing or computing such (parameterized) spectral sums typically involves the matrix decomposition at …

Robust Inference via Generative Classifiers for Handling Noisy Labels

2019 · arXiv (Cornell University)

Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a …

A Simple Randomization Technique for Generalization in Deep Reinforcement Learning

2019 · arXiv (Cornell University)

Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we propose …

Rethinking Data Augmentation: Self-Supervision and Self-Distillation

2019 · arXiv (Cornell University)

Data augmentation techniques, e.g., flipping or cropping, which systematically enlarge the training dataset by explicitly generating more training samples, are effective in improving the generalization performance of deep neural networks. In the supervised setting, a …

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

2020 · arXiv (Cornell University)

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. …

Regularizing Class-Wise Predictions via Self-Knowledge Distillation

2020

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In particular, …

Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation

2022 · arXiv (Cornell University)

The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. To resolve this, recent works focus on developing weaker forms of …

Think Clearly: Improving Reasoning via Redundant Token Pruning

2025 · arXiv (Cornell University)

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial redundancy; analyzing …