Search Results for author: Jiaming Song

Found 52 papers, 29 papers with code

Bridging the Gap Between f-GANs and Wasserstein GANs

1 code implementation ICML 2020 Jiaming Song, Stefano Ermon

Generative adversarial networks (GANs) variants approximately minimize divergences between the model and the data distribution using a discriminator.

Density Ratio Estimation Image Generation

D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation

1 code implementation NeurIPS 2021 Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire.

Conditional Image Generation Image Manipulation +1

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

1 code implementation NeurIPS 2021 Jiayu Chen, Yuanxin Zhang, Yuanfan Xu, Huimin Ma, Huazhong Yang, Jiaming Song, Yu Wang, Yi Wu

We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution.

Curriculum Learning Multi-agent Reinforcement Learning

SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

1 code implementation2 Aug 2021 Chenlin Meng, Yang song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon

We introduce a new image editing and synthesis framework, Stochastic Differential Editing (SDEdit), based on a recent generative model using stochastic differential equations (SDEs).

GAN inversion Image Generation

CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

1 code implementation NeurIPS 2021 Yusuke Tashiro, Jiaming Song, Yang song, Stefano Ermon

In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data.

Image Generation Imputation +1

IQ-Learn: Inverse soft-Q Learning for Imitation

no code implementations NeurIPS 2021 Divyansh Garg, Shuvam Chakraborty, Chris Cundy, Jiaming Song, Stefano Ermon

In many sequential decision-making problems (e. g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task.

Decision Making Imitation Learning +1

D2C: Diffusion-Denoising Models for Few-shot Conditional Generation

2 code implementations12 Jun 2021 Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire.

Conditional Image Generation Denoising +2

Hybrid Mutual Information Lower-bound Estimators for Representation Learning

no code implementations ICLR Workshop Neural_Compression 2021 Abhishek Sinha, Jiaming Song, Stefano Ermon

We illustrate that with one set of representations, the hybrid approach is able to achieve good performance on multiple downstream tasks such as classification, reconstruction, and generation.

Representation Learning

Negative Data Augmentation

2 code implementations ICLR 2021 Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon

Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.

Action Recognition Anomaly Detection +7

H-divergence: A Decision-Theoretic Discrepancy Measure for Two Sample Tests

no code implementations1 Jan 2021 Shengjia Zhao, Abhishek Sinha, Yutong He, Aidan Perreault, Jiaming Song, Stefano Ermon

Based on ideas from decision theory, we investigate a new class of discrepancies that are based on the optimal decision loss.

Autoregressive Score Matching

no code implementations NeurIPS 2020 Chenlin Meng, Lantao Yu, Yang song, Jiaming Song, Stefano Ermon

To increase flexibility, we propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariate log-conditionals (scores), which need not be normalized.

Density Estimation Image Denoising +2

Imitation with Neural Density Models

no code implementations NeurIPS 2021 Kuno Kim, Akshat Jindal, Yang song, Jiaming Song, Yanan Sui, Stefano Ermon

We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward.

Density Estimation Imitation Learning

Denoising Diffusion Implicit Models

5 code implementations ICLR 2021 Jiaming Song, Chenlin Meng, Stefano Ermon

Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample.

Denoising Image Interpolation

Privacy Preserving Recalibration under Domain Shift

no code implementations21 Aug 2020 Rachel Luo, Shengjia Zhao, Jiaming Song, Jonathan Kuck, Stefano Ermon, Silvio Savarese

In an extensive empirical study, we find that our algorithm improves calibration on domain-shift benchmarks under the constraints of differential privacy.

Multi-label Contrastive Predictive Coding

no code implementations NeurIPS 2020 Jiaming Song, Stefano Ermon

We demonstrate that the proposed approach is able to lead to better mutual information estimation, gain empirical improvements in unsupervised representation learning, and beat a current state-of-the-art knowledge distillation method over 10 out of 13 tasks.

Knowledge Distillation Multi-class Classification +3

Experience Replay with Likelihood-free Importance Weights

1 code implementation23 Jun 2020 Samarth Sinha, Jiaming Song, Animesh Garg, Stefano Ermon

The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning.

OpenAI Gym

Robust and On-the-fly Dataset Denoising for Image Classification

no code implementations ECCV 2020 Jiaming Song, Lunjia Hu, Michael Auli, Yann Dauphin, Tengyu Ma

We address this problem by reasoning counterfactually about the loss distribution of examples with uniform random labels had they were trained with the real examples, and use this information to remove noisy examples from the training set.

Classification Denoising +2

Training Deep Energy-Based Models with f-Divergence Minimization

1 code implementation ICML 2020 Lantao Yu, Yang song, Jiaming Song, Stefano Ermon

Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.

Gaussianization Flows

3 code implementations4 Mar 2020 Chenlin Meng, Yang song, Jiaming Song, Stefano Ermon

Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one.

Permutation Invariant Graph Generation via Score-Based Generative Modeling

1 code implementation2 Mar 2020 Chenhao Niu, Yang song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon

In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph (a. k. a., the score function).

Graph Generation

Bridging the Gap Between $f$-GANs and Wasserstein GANs

1 code implementation22 Oct 2019 Jiaming Song, Stefano Ermon

Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions.

Image Generation

Understanding the Limitations of Variational Mutual Information Estimators

1 code implementation ICLR 2020 Jiaming Song, Stefano Ermon

Variational approaches based on neural networks are showing promise for estimating mutual information (MI) between high dimensional variables.

Domain Adaptive Imitation Learning

1 code implementation ICML 2020 Kuno Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon

We formalize the Domain Adaptive Imitation Learning (DAIL) problem, which is a unified framework for imitation learning in the presence of viewpoint, embodiment, and dynamics mismatch.

Imitation Learning

Cross Domain Imitation Learning

no code implementations25 Sep 2019 Kun Ho Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon

Informally, CDIL is the process of learning how to perform a task optimally, given demonstrations of the task in a distinct domain.

Imitation Learning

Multi-Agent Adversarial Inverse Reinforcement Learning

1 code implementation30 Jul 2019 Lantao Yu, Jiaming Song, Stefano Ermon

Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification.

Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

2 code implementations NeurIPS 2019 Aditya Grover, Jiaming Song, Alekh Agarwal, Kenneth Tran, Ashish Kapoor, Eric Horvitz, Stefano Ermon

A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions.

Data Augmentation

Calibrated Model-Based Deep Reinforcement Learning

1 code implementation19 Jun 2019 Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon

Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning.

Model-based Reinforcement Learning

Better Generalization with On-the-fly Dataset Denoising

no code implementations ICLR 2019 Jiaming Song, Tengyu Ma, Michael Auli, Yann Dauphin

Memorization in over-parameterized neural networks can severely hurt generalization in the presence of mislabeled examples.

Denoising

Bias Correction of Learned Generative Models via Likelihood-free Importance Weighting

no code implementations ICLR Workshop DeepGenStruct 2019 Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric Horvitz, Stefano Ermon

A standard technique to correct this bias is by importance weighting samples from the model by the likelihood ratio under the model and true distributions.

Data Augmentation

Learning Controllable Fair Representations

3 code implementations11 Dec 2018 Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, Stefano Ermon

Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data.

Fairness

Multi-Agent Generative Adversarial Imitation Learning

1 code implementation NeurIPS 2018 Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon

Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal.

Imitation Learning

The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models

2 code implementations18 Jun 2018 Shengjia Zhao, Jiaming Song, Stefano Ermon

A large number of objectives have been proposed to train latent variable generative models.

Adversarial Constraint Learning for Structured Prediction

1 code implementation27 May 2018 Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws.

Pose Estimation Structured Prediction +2

Accelerating Natural Gradient with Higher-Order Invariance

2 code implementations ICML 2018 Yang Song, Jiaming Song, Stefano Ermon

An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model.

An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients

no code implementations17 Jan 2018 Jiaming Song, Yuhuai Wu

In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC.

Learning Hierarchical Features from Deep Generative Models

no code implementations ICML 2017 Shengjia Zhao, Jiaming Song, Stefano Ermon

In this paper, we prove that hierarchical latent variable models do not take advantage of the hierarchical structure when trained with existing variational methods, and provide some limitations on the kind of features existing models can learn.

Hierarchical structure Latent Variable Models

A-NICE-MC: Adversarial Training for MCMC

3 code implementations NeurIPS 2017 Jiaming Song, Shengjia Zhao, Stefano Ermon

We propose A-NICE-MC, a novel method to train flexible parametric Markov chain kernels to produce samples with desired properties.

InfoVAE: Information Maximizing Variational Autoencoders

6 code implementations7 Jun 2017 Shengjia Zhao, Jiaming Song, Stefano Ermon

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models.

InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations

4 code implementations NeurIPS 2017 Yunzhu Li, Jiaming Song, Stefano Ermon

The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal.

Imitation Learning

On the Limits of Learning Representations with Label-Based Supervision

no code implementations7 Mar 2017 Jiaming Song, Russell Stewart, Shengjia Zhao, Stefano Ermon

Advances in neural network based classifiers have transformed automatic feature learning from a pipe dream of stronger AI to a routine and expected property of practical systems.

Representation Learning Transfer Learning

Towards Deeper Understanding of Variational Autoencoding Models

2 code implementations28 Feb 2017 Shengjia Zhao, Jiaming Song, Stefano Ermon

We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound.

Learning Hierarchical Features from Generative Models

3 code implementations27 Feb 2017 Shengjia Zhao, Jiaming Song, Stefano Ermon

In this paper, we prove that hierarchical latent variable models do not take advantage of the hierarchical structure when trained with existing variational methods, and provide some limitations on the kind of features existing models can learn.

Hierarchical structure Latent Variable Models

Factored Temporal Sigmoid Belief Networks for Sequence Learning

no code implementations22 May 2016 Jiaming Song, Zhe Gan, Lawrence Carin

Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences.

Classification General Classification

Max-Margin Nonparametric Latent Feature Models for Link Prediction

no code implementations24 Feb 2016 Jun Zhu, Jiaming Song, Bei Chen

Our approach attempts to unite the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction.

Link Prediction Variational Inference

Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation

no code implementations7 Dec 2015 Bei Chen, Ning Chen, Jun Zhu, Jiaming Song, Bo Zhang

We present a discriminative nonparametric latent feature relational model (LFRM) for link prediction to automatically infer the dimensionality of latent features.

Bayesian Inference Data Augmentation +1

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