Search Results for author:
Found 88 papers, 49 papers with code
Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.
Bridging the Gap Between Value and Policy Based Reinforcement Learning
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization.
Filtering Variational Objectives
When used as a surrogate objective for maximum likelihood estimation in latent variable models, the evidence lower bound (ELBO) produces state-of-the-art results.
A Simple Framework for Contrastive Learning of Visual Representations
This paper presents SimCLR: a simple framework for contrastive learning of visual representations.
Ranked #4 on
Contrastive Learning
on imagenet-1k
Contrastive Learning
Self-Supervised Image Classification
+3
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object.
Similarity of Neural Network Representations Revisited
We introduce a similarity index that measures the relationship between representational similarity matrices and does not suffer from this limitation.
Learning to Generalize from Sparse and Underspecified Rewards
The parameters of the auxiliary reward function are optimized with respect to the validation performance of a trained policy.
Dream to Control: Learning Behaviors by Latent Imagination
Learned world models summarize an agent's experience to facilitate learning complex behaviors.
WaveGrad: Estimating Gradients for Waveform Generation
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density.
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder.
Ranked #35 on
Machine Translation
on WMT2014 English-French
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding.
Ranked #17 on
Text-to-Image Generation
on MS COCO
(using extra training data)
Big Self-Supervised Models are Strong Semi-Supervised Learners
The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2, supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge.
Self-Supervised Image Classification
Semi-Supervised Image Classification
Image Super-Resolution via Iterative Refinement
We present SR3, an approach to image Super-Resolution via Repeated Refinement.
Mastering Atari with Discrete World Models
The world model uses discrete representations and is trained separately from the policy.
Ranked #3 on
Atari Games
on Atari 2600 Skiing
(using extra training data)
Video Diffusion Models
Generating temporally coherent high fidelity video is an important milestone in generative modeling research.
Robust and Efficient Medical Imaging with Self-Supervision
These results suggest that REMEDIS can significantly accelerate the life-cycle of medical imaging AI development thereby presenting an important step forward for medical imaging AI to deliver broad impact.
Palette: Image-to-Image Diffusion Models
We expect this standardized evaluation protocol to play a role in advancing image-to-image translation research.
Ranked #1 on
Colorization
on ImageNet ctest10k
Zero-Shot Learning by Convex Combination of Semantic Embeddings
In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage.
Ranked #8 on
Multi-label zero-shot learning
on Open Images V4
Neural Combinatorial Optimization with Reinforcement Learning
Despite the computational expense, without much engineering and heuristic designing, Neural Combinatorial Optimization achieves close to optimal results on 2D Euclidean graphs with up to 100 nodes.
An Optimistic Perspective on Offline Reinforcement Learning
The DQN replay dataset can serve as an offline RL benchmark and is open-sourced.
An Optimistic Perspective on Offline Deep Reinforcement Learning
The DQN replay dataset can serve as an offline RL benchmark and is open-sourced.
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y).
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate.
Fast Exact Search in Hamming Space with Multi-Index Hashing
There is growing interest in representing image data and feature descriptors using compact binary codes for fast near neighbor search.
Character-Aware Models Improve Visual Text Rendering
In the text-only domain, we find that character-aware models provide large gains on a novel spelling task (WikiSpell).
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets.
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
On the SQuAD dataset, our model is 3x to 13x faster in training and 4x to 9x faster in inference, while achieving equivalent accuracy to recurrent models.
Ranked #27 on
Question Answering
on SQuAD1.1 dev
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform.
TryOnDiffusion: A Tale of Two UNets
Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person.
Benchmarks for Deep Off-Policy Evaluation
Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making.
Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation
We introduce Exemplar VAEs, a family of generative models that bridge the gap between parametric and non-parametric, exemplar based generative models.
No MCMC for me: Amortized sampling for fast and stable training of energy-based models
Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty.
Imputer: Sequence Modelling via Imputation and Dynamic Programming
This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations.
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
We approach structured output prediction by optimizing a deep value network (DVN) to precisely estimate the task loss on different output configurations for a given input.
Cartesian K-Means
A fundamental limitation of quantization techniques like the k-means clustering algorithm is the storage and runtime cost associated with the large numbers of clusters required to keep quantization errors small and model fidelity high.
Understanding the impact of entropy on policy optimization
Entropy regularization is commonly used to improve policy optimization in reinforcement learning.
Decoder Denoising Pretraining for Semantic Segmentation
We propose a decoder pretraining approach based on denoising, which can be combined with supervised pretraining of the encoder.
Device Placement Optimization with Reinforcement Learning
Key to our method is the use of a sequence-to-sequence model to predict which subsets of operations in a TensorFlow graph should run on which of the available devices.
Non-Autoregressive Machine Translation with Latent Alignments
In addition, we adapt the Imputer model for non-autoregressive machine translation and demonstrate that Imputer with just 4 generation steps can match the performance of an autoregressive Transformer baseline.
Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units.
Optimal Completion Distillation for Sequence Learning
We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance.
Big Self-Supervised Models Advance Medical Image Classification
Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis.
Detecting Cancer Metastases on Gigapixel Pathology Images
At 8 false positives per image, we detect 92. 4% of the tumors, relative to 82. 7% by the previous best automated approach.
Ranked #2 on
Medical Object Detection
on Barrett’s Esophagus
Generate, Annotate, and Learn: NLP with Synthetic Text
This paper studies the use of language models as a source of synthetic unlabeled text for NLP.
Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC).
Embedding Text in Hyperbolic Spaces
Ideally, we could incorporate our prior knowledge of this hierarchical structure into unsupervised learning algorithms that work on text data.
Smoothed Action Value Functions for Learning Gaussian Policies
State-action value functions (i. e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning.
N-gram Language Modeling using Recurrent Neural Network Estimation
Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell with dropout to be the best model for encoding the $n$-gram state when compared with feed-forward and vanilla RNN models.
PixColor: Pixel Recursive Colorization
Then, given the generated low-resolution color image and the original grayscale image as inputs, we train a second CNN to generate a high-resolution colorization of an image.
Ranked #3 on
Colorization
on ImageNet val
Pixel Recursive Super Resolution
A low resolution image may correspond to multiple plausible high resolution images, thus modeling the super resolution process with a pixel independent conditional model often results in averaging different details--hence blurry edges.
Improving Policy Gradient by Exploring Under-appreciated Rewards
We propose a more directed exploration strategy that promotes exploration of under-appreciated reward regions.
Reward Augmented Maximum Likelihood for Neural Structured Prediction
A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation.
Efficient non-greedy optimization of decision trees
In this paper, we present an algorithm for optimizing the split functions at all levels of the tree jointly with the leaf parameters, based on a global objective.
CO2 Forest: Improved Random Forest by Continuous Optimization of Oblique Splits
We develop a convex-concave upper bound on the classification loss for a one-level decision tree, and optimize the bound by stochastic gradient descent at each internal node of the tree.
The Importance of Generation Order in Language Modeling
Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks.
Sequence to Sequence Mixture Model for Diverse Machine Translation
In this paper, we develop a novel sequence to sequence mixture (S2SMIX) model that improves both translation diversity and quality by adopting a committee of specialized translation models rather than a single translation model.
Contingency-Aware Exploration in Reinforcement Learning
This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning.
Ranked #8 on
Atari Games
on Atari 2600 Montezuma's Revenge
Hamming Distance Metric Learning
Motivated by large-scale multimedia applications we propose to learn mappings from high-dimensional data to binary codes that preserve semantic similarity.
Code Synthesis with Priority Queue Training
We consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards.
Learning Gaussian Policies from Smoothed Action Value Functions
We propose a new notion of action value defined by a Gaussian smoothed version of the expected Q-value used in SARSA.
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow.
Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
Posterior collapse in Variational Autoencoders (VAEs) arises when the variational posterior distribution closely matches the prior for a subset of latent variables.
NASA: Neural Articulated Shape Approximation
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics.
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest.
NiLBS: Neural Inverse Linear Blend Skinning
In this technical report, we investigate efficient representations of articulated objects (e. g. human bodies), which is an important problem in computer vision and graphics.
NASA Neural Articulated Shape Approximation
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics.
Demystifying Loss Functions for Classification
It is common to use the softmax cross-entropy loss to train neural networks on classification datasets where a single class label is assigned to each example.
Why Do Better Loss Functions Lead to Less Transferable Features?
We show that many objectives lead to statistically significant improvements in ImageNet accuracy over vanilla softmax cross-entropy, but the resulting fixed feature extractors transfer substantially worse to downstream tasks, and the choice of loss has little effect when networks are fully fine-tuned on the new tasks.
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal.
Ranked #1 on
Speech Recognition
on Switchboard CallHome
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization
This modeling choice assumes that different dimensions of the next state and reward are conditionally independent given the current state and action and may be driven by the fact that fully observable physics-based simulation environments entail deterministic transition dynamics.
Learning to Efficiently Sample from Diffusion Probabilistic Models
Key advantages of DDPMs include ease of training, in contrast to generative adversarial networks, and speed of generation, in contrast to autoregressive models.
Cascaded Diffusion Models for High Fidelity Image Generation
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality.
Ranked #3 on
Image Generation
on ImageNet 64x64
Optimizing Few-Step Diffusion Samplers by Gradient Descent
We propose Generalized Gaussian Diffusion Processes (GGDP), a family of non-Markovian samplers for diffusion models, and we show how to improve the generated samples of pre-trained DDPMs by optimizing the degrees of freedom of the GGDP sampler family with respect to a perceptual loss.
Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation
To obtain strong task-specific generative models, we either fine-tune a large language model (LLM) on inputs from specific tasks, or prompt a LLM with a few input examples to generate more unlabeled examples.
Understanding Posterior Collapse in Generative Latent Variable Models
Posterior collapse in Variational Autoencoders (VAEs) arises when the variational distribution closely matches the uninformative prior for a subset of latent variables.
Striving for Simplicity in Off-Policy Deep Reinforcement Learning
This paper advocates the use of offline (batch) reinforcement learning (RL) to help (1) isolate the contributions of exploitation vs. exploration in off-policy deep RL, (2) improve reproducibility of deep RL research, and (3) facilitate the design of simpler deep RL algorithms.
Self-Imitation Learning via Trajectory-Conditioned Policy for Hard-Exploration Tasks
We propose a new method of learning a trajectory-conditioned policy to imitate diverse trajectories from the agent's own past experiences and show that such self-imitation helps avoid myopic behavior and increases the chance of finding a globally optimal solution for hard-exploration tasks, especially when there are misleading rewards.
Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
We introduce Differentiable Diffusion Sampler Search (DDSS): a method that optimizes fast samplers for any pre-trained diffusion model by differentiating through sample quality scores.
Imagen Video: High Definition Video Generation with Diffusion Models
We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models.
Ranked #1 on
Video Generation
on LAION-400M
Novel View Synthesis with Diffusion Models
We demonstrate that stochastic conditioning significantly improves the 3D consistency of a naive sampler for an image-to-image diffusion model, which involves conditioning on a single fixed view.
Meta-Learning Fast Weight Language Models
Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance.
Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting
Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.
Monocular Depth Estimation using Diffusion Models
To cope with the limited availability of data for supervised training, we leverage pre-training on self-supervised image-to-image translation tasks.
Ranked #21 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Synthetic Data from Diffusion Models Improves ImageNet Classification
Deep generative models are becoming increasingly powerful, now generating diverse high fidelity photo-realistic samples given text prompts.
The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity.
