Search Results for author:
Found 215 papers, 115 papers with code
Bridging the Gap Between f-GANs and Wasserstein GANs
Generative adversarial networks (GANs) variants approximately minimize divergences between the model and the data distribution using a discriminator.
End-to-End Diffusion Latent Optimization Improves Classifier Guidance
Classifier guidance -- using the gradients of an image classifier to steer the generations of a diffusion model -- has the potential to dramatically expand the creative control over image generation and editing.
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation.
HIVE: Harnessing Human Feedback for Instructional Visual Editing
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching
In this case, a well-known issue is the distribution shift between the learned policy and the behavior policy that collects the offline data.
Hyena Hierarchy: Towards Larger Convolutional Language Models
Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale.
Ranked #25 on
Language Modelling
on WikiText-103
Long Horizon Temperature Scaling
LHTS is compatible with all likelihood-based models, and optimizes for the long-horizon likelihood of samples.
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
Pre-trained diffusion models have been successfully used as priors in a variety of linear inverse problems, where the goal is to reconstruct a signal from noisy linear measurements.
Extreme Q-Learning: MaxEnt RL without Entropy
Using EVT, we derive our \emph{Extreme Q-Learning} framework and consequently online and, for the first time, offline MaxEnt Q-learning algorithms, that do not explicitly require access to a policy or its entropy.
Building Coverage Estimation with Low-resolution Remote Sensing Imagery
In this paper, we propose a method for estimating building coverage using only publicly available low-resolution satellite imagery that is more frequently updated.
Deep Latent State Space Models for Time-Series Generation
Methods based on ordinary differential equations (ODEs) are widely used to build generative models of time-series.
Transform Once: Efficient Operator Learning in Frequency Domain
Instead, this work introduces a blueprint for frequency domain learning through a single transform: transform once (T1).
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
With 1. 2%-area edited regions, our method reduces the computation of DDIM by 7. 5$\times$ and GauGAN by 18$\times$ while preserving the visual fidelity.
Concrete Score Matching: Generalized Score Matching for Discrete Data
To this end, we propose an analogous score function called the "Concrete score", a generalization of the (Stein) score for discrete settings.
LMPriors: Pre-Trained Language Models as Task-Specific Priors
Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors.
Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation
Score-based generative models learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise.
Exploration via Planning for Information about the Optimal Trajectory
In this work, we develop a method that allows us to plan for exploration while taking both the task and the current knowledge about the dynamics into account.
On Distillation of Guided Diffusion Models
For standard diffusion models trained on the pixel-space, our approach is able to generate images visually comparable to that of the original model using as few as 4 sampling steps on ImageNet 64x64 and CIFAR-10, achieving FID/IS scores comparable to that of the original model while being up to 256 times faster to sample from.
Generalizing Bayesian Optimization with Decision-theoretic Entropies
Bayesian optimization (BO) is a popular method for efficiently inferring optima of an expensive black-box function via a sequence of queries.
Towards General-Purpose Representation Learning of Polygonal Geometries
For the spatial domain approach, we propose ResNet1D, a 1D CNN-based polygon encoder, which uses circular padding to achieve loop origin invariance on simple polygons.
ButterflyFlow: Building Invertible Layers with Butterfly Matrices
Normalizing flows model complex probability distributions using maps obtained by composing invertible layers.
JPEG Artifact Correction using Denoising Diffusion Restoration Models
Diffusion models can be used as learned priors for solving various inverse problems.
Improving Self-Supervised Learning by Characterizing Idealized Representations
For non-contrastive learning, we use our framework to derive a simple and novel objective.
Efficient Tuning of Particle Accelerator Emittance via Bayesian Algorithm Execution and Virtual Objectives
Traditional black-box optimizers such as Bayesian optimization are slow and inefficient when dealing with such objectives as they must acquire the full series of measurements, but return only the emittance, with each query.
SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery
Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks.
A General Recipe for Likelihood-free Bayesian Optimization
To extend BO to a broader class of models and utilities, we propose likelihood-free BO (LFBO), an approach based on likelihood-free inference.
Modular Conformal Calibration
We introduce a versatile class of algorithms for recalibration in regression that we call Modular Conformal Calibration (MCC).
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
We also extend FlashAttention to block-sparse attention, yielding an approximate attention algorithm that is faster than any existing approximate attention method.
Training and Inference on Any-Order Autoregressive Models the Right Way
Conditional inference on arbitrary subsets of variables is a core problem in probabilistic inference with important applications such as masked language modeling and image inpainting.
Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations
We investigate how to leverage the representations produced by Neural Collages in various tasks, including data compression and generation.
Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-Resolution
Automated tracking of urban development in areas where construction information is not available became possible with recent advancements in machine learning and remote sensing.
Generative Modeling Helps Weak Supervision (and Vice Versa)
The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples.
Dual Diffusion Implicit Bridges for Image-to-Image Translation
Image translation with DDIBs relies on two diffusion models trained independently on each domain, and is a two-step process: DDIBs first obtain latent encodings for source images with the source diffusion model, and then decode such encodings using the target model to construct target images.
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.
LISA: Learning Interpretable Skill Abstractions from Language
Learning policies that effectively utilize language instructions in complex, multi-task environments is an important problem in sequential decision-making.
Imitation Learning by Estimating Expertise of Demonstrators
In this work, we show that unsupervised learning over demonstrator expertise can lead to a consistent boost in the performance of imitation learning algorithms.
Denoising Diffusion Restoration Models
Many interesting tasks in image restoration can be cast as linear inverse problems.
Conditional Imitation Learning for Multi-Agent Games
In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time.
IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling
We show empirically that the proposed framework achieves strong performance on estimating the number of buildings in the United States and Africa, cars in Kenya, brick kilns in Bangladesh, and swimming pools in the U. S., while requiring as few as 0. 01% of satellite images compared to an exhaustive approach.
Quantifying and Understanding Adversarial Examples in Discrete Input Spaces
In this work, we seek to understand and extend adversarial examples across domains in which inputs are discrete, particularly across new domains, such as computational biology.
An Experimental Design Perspective on Model-Based Reinforcement Learning
In particular, we leverage ideas from Bayesian optimal experimental design to guide the selection of state-action queries for efficient learning.
A Unified Framework for Multi-distribution Density Ratio Estimation
Binary density ratio estimation (DRE), the problem of estimating the ratio $p_1/p_2$ given their empirical samples, provides the foundation for many state-of-the-art machine learning algorithms such as contrastive representation learning and covariate shift adaptation.
BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery
We propose Bayesian Causal Discovery Nets (BCD Nets), a variational inference framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM.
HyperSPNs: Compact and Expressive Probabilistic Circuits
Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions.
D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation
Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire.
Reliable Decisions with Threshold Calibration
We propose a stronger notion of calibration called threshold calibration, which is exactly the condition required to ensure that decision loss is predicted accurately for threshold decisions.
Density Ratio Estimation via Infinitesimal Classification
We then estimate the instantaneous rate of change of the bridge distributions indexed by time (the "time score") -- a quantity defined analogously to data (Stein) scores -- with a novel time score matching objective.
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
These measurements are typically synthesized from images using a fixed physical model of the measurement process, which hinders the generalization capability of models to unknown measurement processes.
SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning
Our goals for SustainBench are to (1) lower the barriers to entry for the machine learning community to contribute to measuring and achieving the SDGs; (2) provide standard benchmarks for evaluating machine learning models on tasks across a variety of SDGs; and (3) encourage the development of novel machine learning methods where improved model performance facilitates progress towards the SDGs.
Estimating High Order Gradients of the Data Distribution by Denoising
By leveraging Tweedie's formula on higher order moments, we generalize denoising score matching to estimate higher order derivatives.
Pseudo-Spherical Contrastive Divergence
Energy-based models (EBMs) offer flexible distribution parametrization.
H-Entropy Search: Generalizing Bayesian Optimization with a Decision-theoretic Uncertainty Measure
For special cases of the loss and design space, we develop gradient-based methods to efficiently optimize our proposed family of acquisition functions, and demonstrate that the resulting BO procedure shows strong empirical performance on a diverse set of optimization tasks.
Sphere2Vec: Self-Supervised Location Representation Learning on Spherical Surfaces
Location encoding is valuable for a multitude of tasks where both the absolute positions and local contexts (image, text, and other types of metadata) of spatial objects are needed for accurate predictions.
An Experimental Design Perspective on Exploration in Reinforcement Learning
In particular, we leverage ideas from Bayesian optimal experimental design to guide the selection of state-action queries for efficient learning.
Provably Calibrated Regression Under Distribution Drift
Accurate uncertainty quantification is a key building block of trustworthy machine learning systems.
Mind Your Bits and Errors: Prioritizing the Bits that Matter in Variational Autoencoders
In this work, we consider the task of image generative modeling with variational autoencoders and posit that the nature of high-dimensional image data distributions poses an intrinsic challenge.
Comparing Distributions by Measuring Differences that Affect Decision Making
Measuring the discrepancy between two probability distributions is a fundamental problem in machine learning and statistics.
Equivariant Neural Network for Factor Graphs
Several indices used in a factor graph data structure can be permuted without changing the underlying probability distribution.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
The key challenge is balancing faithfulness to the user input (e. g., hand-drawn colored strokes) and realism of the synthesized image.
Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration
In this work, we introduce a new notion -- \emph{decision calibration} -- that requires the predicted distribution and true distribution to be ``indistinguishable'' to a set of downstream decision-makers.
Multi-Agent Imitation Learning with Copulas
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems.
CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
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.
Featurized Density Ratio Estimation
Density ratio estimation serves as an important technique in the unsupervised machine learning toolbox.
IQ-Learn: Inverse soft-Q Learning for Imitation
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.
Ranked #1 on
MuJoCo Games
on Walker2d
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
High-resolution satellite imagery has proven useful for a broad range of tasks, including measurement of global human population, local economic livelihoods, and biodiversity, among many others.
Temporal Predictive Coding For Model-Based Planning In Latent Space
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire.
Improving Compositionality of Neural Networks by Decoding Representations to Inputs
In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together.
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Given such an $\mathcal{A}$, and a prior distribution over $f$, we refer to the problem of inferring the output of $\mathcal{A}$ using $T$ evaluations as Bayesian Algorithm Execution (BAX).
On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Humans can quickly adapt to new partners in collaborative tasks (e. g. playing basketball), because they understand which fundamental skills of the task (e. g. how to dribble, how to shoot) carry over across new partners.
Improved Autoregressive Modeling with Distribution Smoothing
While autoregressive models excel at image compression, their sample quality is often lacking.
Hybrid Mutual Information Lower-bound Estimators for Representation Learning
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.
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.
Local Calibration: Metrics and Recalibration
In this work, we propose the local calibration error (LCE) to span the gap between average and individual reliability.
Neural Network Compression for Noisy Storage Devices
Compression and efficient storage of neural network (NN) parameters is critical for applications that run on resource-constrained devices.
Negative Data Augmentation
Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.
Ranked #6 on
Image Generation
on CIFAR-100
Maximum Likelihood Training of Score-Based Diffusion Models
Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses.
Ranked #5 on
Image Generation
on ImageNet 32x32
(bpd metric)
Non-Markovian Predictive Coding For Planning In Latent Space
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.
Understanding Classifiers with Generative Models
Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle.
H-divergence: A Decision-Theoretic Discrepancy Measure for Two Sample Tests
Based on ideas from decision theory, we investigate a new class of discrepancies that are based on the optimal decision loss.
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions.
PiRank: Scalable Learning To Rank via Differentiable Sorting
A key challenge with machine learning approaches for ranking is the gap between the performance metrics of interest and the surrogate loss functions that can be optimized with gradient-based methods.
Score-Based Generative Modeling through Stochastic Differential Equations
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
Ranked #11 on
Image Generation
on CIFAR-10
Efficient Conditional Pre-training for Transfer Learning
Finally, we improve standard ImageNet pre-training by 1-3% by tuning available models on our subsets and pre-training on a dataset filtered from a larger scale dataset.
Geography-Aware Self-Supervised Learning
Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks.
Ranked #1 on
Semantic Segmentation
on SpaceNet 1
(using extra training data)
Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
Decision makers often need to rely on imperfect probabilistic forecasts.
Autoregressive Score Matching
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.
Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Inference in discrete graphical models with variational methods is difficult because of the inability to re-parameterize gradients of the Evidence Lower Bound (ELBO).
Imitation with Neural Density Models
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.
Noisy Neural Network Compression for Analog Storage Devices
Efficient compression and storage of neural network (NN) parameters is critical for resource-constrained, downstream machine learning applications.
Denoising Diffusion Implicit Models
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.
Understanding Classifier Mistakes with Generative Models
From this observation, we develop a detection criteria for samples on which a classifier is likely to fail at test time.
Privacy Preserving Recalibration under Domain Shift
In an extensive empirical study, we find that our algorithm improves calibration on domain-shift benchmarks under the constraints of differential privacy.
HiPPO: Recurrent Memory with Optimal Polynomial Projections
A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed.
Ranked #7 on
Sequential Image Classification
on Sequential MNIST
Multi-label Contrastive Predictive Coding
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.
Efficient Learning of Generative Models via Finite-Difference Score Matching
Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.
Belief Propagation Neural Networks
Learned neural solvers have successfully been used to solve combinatorial optimization and decision problems.
Unsupervised Calibration under Covariate Shift
A probabilistic model is said to be calibrated if its predicted probabilities match the corresponding empirical frequencies.
Experience Replay with Likelihood-free Importance Weights
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.
A Framework for Sample Efficient Interval Estimation with Control Variates
We consider the problem of estimating confidence intervals for the mean of a random variable, where the goal is to produce the smallest possible interval for a given number of samples.
Individual Calibration with Randomized Forecasting
We show that calibration for individual samples is possible in the regression setup if the predictions are randomized, i. e. outputting randomized credible intervals.
Improved Techniques for Training Score-Based Generative Models
Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization.
Ranked #66 on
Image Generation
on CIFAR-10
Predicting Livelihood Indicators from Community-Generated Street-Level Imagery
Major decisions from governments and other large organizations rely on measurements of the populace's well-being, but making such measurements at a broad scale is expensive and thus infrequent in much of the developing world.
Efficient Poverty Mapping using Deep Reinforcement Learning
The combination of high-resolution satellite imagery and machine learning have proven useful in many sustainability-related tasks, including poverty prediction, infrastructure measurement, and forest monitoring.
Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
Learning disentangled representations is regarded as a fundamental task for improving the generalization, robustness, and interpretability of generative models.
MOPO: Model-based Offline Policy Optimization
We also characterize the trade-off between the gain and risk of leaving the support of the batch data.
Farmland Parcel Delineation Using Spatio-temporal Convolutional Networks
Using satellite imaging can be a scalable and cost effective manner to perform the task of farm parcel delineation to collect this valuable data.
Diversity can be Transferred: Output Diversification for White- and Black-box Attacks
Adversarial attacks often involve random perturbations of the inputs drawn from uniform or Gaussian distributions, e. g., to initialize optimization-based white-box attacks or generate update directions in black-box attacks.
Training Deep Energy-Based Models with f-Divergence Minimization
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
Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one.
Predictive Coding for Locally-Linear Control
High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks.
Permutation Invariant Graph Generation via Score-Based Generative Modeling
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).
Learning When and Where to Zoom with Deep Reinforcement Learning
While high resolution images contain semantically more useful information than their lower resolution counterparts, processing them is computationally more expensive, and in some applications, e. g. remote sensing, they can be much more expensive to acquire.
A Theory of Usable Information Under Computational Constraints
We propose a new framework for reasoning about information in complex systems.
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
Feedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning.
Generating Interpretable Poverty Maps using Object Detection in Satellite Images
Accurate local-level poverty measurement is an essential task for governments and humanitarian organizations to track the progress towards improving livelihoods and distribute scarce resources.
Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks
In contrast, we cast the problem of cloud removal as a conditional image synthesis challenge, and we propose a trainable spatiotemporal generator network (STGAN) to remove clouds.
Ranked #2 on
Cloud Removal
on SEN12MS-CR-TS
Efficient Object Detection in Large Images using Deep Reinforcement Learning
Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images.
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.
Learning representations that accurately capture long-range dependencies in sequential inputs --- including text, audio, and genomic data --- is a key problem in deep learning.
Ranked #6 on
Audio Super-Resolution
on VCTK Multi-Speaker
Approximating Human Judgment of Generated Image Quality
Generative models have made immense progress in recent years, particularly in their ability to generate high quality images.
Approximating the Permanent by Sampling from Adaptive Partitions
Computing the permanent of a non-negative matrix is a core problem with practical applications ranging from target tracking to statistical thermodynamics.
Fair Generative Modeling via Weak Supervision
Real-world datasets are often biased with respect to key demographic factors such as race and gender.
Weakly Supervised Disentanglement with Guarantees
Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning.
Bridging the Gap Between $f$-GANs and Wasserstein GANs
Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions.
Unsupervised Out-of-Distribution Detection with Batch Normalization
Based on this insight, we propose to exploit in-batch dependencies for OoD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Understanding the Limitations of Variational Mutual Information Estimators
Variational approaches based on neural networks are showing promise for estimating mutual information (MI) between high dimensional variables.
Domain Adaptive Imitation Learning
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.
Towards Certified Defense for Unrestricted Adversarial Attacks
Our defense draws inspiration from differential privacy, and is based on intentionally adding noise to the classifier's outputs to limit the attacker's knowledge about the parameters.
Cross Domain Imitation Learning
Informally, CDIL is the process of learning how to perform a task optimally, given demonstrations of the task in a distinct domain.
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
Critically, our model can infer rewards for new, structurally-similar tasks from a single demonstration.
Ranked #1 on
MuJoCo Games
on Sawyer Pusher
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning.
Ranked #2 on
Audio Super-Resolution
on Voice Bank corpus (VCTK)
Multi-Agent Adversarial Inverse Reinforcement Learning
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification.
MintNet: Building Invertible Neural Networks with Masked Convolutions
To demonstrate their flexibility, we show that our invertible neural networks are competitive with ResNets on MNIST and CIFAR-10 classification.
Ranked #4 on
Image Generation
on MNIST
Generative Modeling by Estimating Gradients of the Data Distribution
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
Ranked #101 on
Image Generation
on CIFAR-10
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
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.
Calibrated Model-Based Deep Reinforcement Learning
Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning.
Model-based Reinforcement Learning
reinforcement-learning
+1
Learning Neural PDE Solvers with Convergence Guarantees
Partial differential equations (PDEs) are widely used across the physical and computational sciences.
AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows
Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain.
Sliced Score Matching: A Scalable Approach to Density and Score Estimation
However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions.
Learning to Interpret Satellite Images in Global Scale Using Wikipedia
Despite recent progress in computer vision, finegrained interpretation of satellite images remains challenging because of a lack of labeled training data.
Predicting Economic Development using Geolocated Wikipedia Articles
Progress on the UN Sustainable Development Goals (SDGs) is hampered by a persistent lack of data regarding key social, environmental, and economic indicators, particularly in developing countries.
Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
Millions of people worldwide are absent from their country's census.
Distributed generation of privacy preserving data with user customization
Distributed devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the data.
Bias Correction of Learned Generative Models via Likelihood-free Importance Weighting
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.
Stochastic Optimization of Sorting Networks via Continuous Relaxations
Sorting input objects is an important step in many machine learning pipelines.
Training Variational Autoencoders with Buffered Stochastic Variational Inference
The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets.