Search Results for author:
Found 46 papers, 26 papers with code
Directly Fine-Tuning Diffusion Models on Differentiable Rewards
We present Direct Reward Fine-Tuning (DRaFT), a simple and effective method for fine-tuning diffusion models to maximize differentiable reward functions, such as scores from human preference models.
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
We propose an evolution strategies-based algorithm for estimating gradients in unrolled computation graphs, called ES-Single.
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e. g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks.
CUF: Continuous Upsampling Filters
Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited.
Learning to Improve Code Efficiency
To automatically learn these hints from the dataset, we propose a novel discrete variational auto-encoder, where each discrete latent variable represents a different learned category of code-edit that increases performance.
Pre-training helps Bayesian optimization too
Contrary to a common belief that BO is suited to optimizing black-box functions, it actually requires domain knowledge on characteristics of those functions to deploy BO successfully.
Data-Driven Offline Optimization For Architecting Hardware Accelerators
An alternative paradigm is to use a "data-driven", offline approach that utilizes logged simulation data, to architect hardware accelerators, without needing any form of simulations.
Pre-trained Gaussian processes for Bayesian optimization
Contrary to a common expectation that BO is suited to optimizing black-box functions, it actually requires domain knowledge about those functions to deploy BO successfully.
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
We are the first to take a unified perspective to jointly explain the oversmoothing and heterophily problems at the node level.
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables.
Apollo: Transferable Architecture Exploration
We further show that by transferring knowledge between target architectures with different design constraints, Apollo is able to find optimal configurations faster and often with better objective value (up to 25% improvements).
Human 3D keypoints via spatial uncertainty modeling
We introduce a technique for 3D human keypoint estimation that directly models the notion of spatial uncertainty of a keypoint.
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.
Learned Hardware/Software Co-Design of Neural Accelerators
The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning.
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
We develop several scalable techniques to solve the matching problem, and also draw connections to various notions of user regret and fairness, arguing that these outcomes are fairer in a utilitarian sense.
An Imitation Learning Approach for Cache Replacement
While directly applying Belady's is infeasible since the future is unknown, we train a policy conditioned only on past accesses that accurately approximates Belady's even on diverse and complex access patterns, and call this approach Parrot.
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
Neural Execution Engines: Learning to Execute Subroutines
A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms.
SentenceMIM: A Latent Variable Language Model
MIM learning encourages high mutual information between observations and latent variables, and is robust against posterior collapse.
Ranked #1 on
Question Answering
on YahooCQA
(using extra training data)
NEURAL EXECUTION ENGINES
Turing complete computation and reasoning are often regarded as necessary pre- cursors to general intelligence.
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).
MIM: Mutual Information Machine
Experiments show that MIM learns representations with high mutual information, consistent encoding and decoding distributions, effective latent clustering, and data log likelihood comparable to VAE, while avoiding posterior collapse.
High Mutual Information in Representation Learning with Symmetric Variational Inference
We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework.
Learning Execution through Neural Code Fusion
In this work, we propose a new approach to use GNNs to learn fused representations of general source code and its execution.
Flexibly Fair Representation Learning by Disentanglement
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes.
Learning Sparse Networks Using Targeted Dropout
Before computing the gradients for each weight update, targeted dropout stochastically selects a set of units or weights to be dropped using a simple self-reinforcing sparsity criterion and then computes the gradients for the remaining weights.
Graph Normalizing Flows
We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation.
Neural Networks for Modeling Source Code Edits
In this work, we instead treat source code as a dynamic object and tackle the problem of modeling the edits that software developers make to source code files.
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Few-shot classification refers to learning a classifier for new classes given only a few examples.
Ranked #7 on
Few-Shot Image Classification
on Meta-Dataset Rank
Targeted Dropout
Neural networks are extremely flexible models due to their large number of parameters, which is beneficial for learning, but also highly redundant.
Learning Memory Access Patterns
In this paper, we demonstrate the potential of deep learning to address the von Neumann bottleneck of memory performance.
Meta-Learning for Semi-Supervised Few-Shot Classification
To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes.
An online sequence-to-sequence model for noisy speech recognition
This is because the models require that the entirety of the input sequence be available at the beginning of inference, an assumption that is not valid for instantaneous speech recognition.
Learning Hard Alignments with Variational Inference
There has recently been significant interest in hard attention models for tasks such as object recognition, visual captioning and speech recognition.
Prototypical Networks for Few-shot Learning
We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.
The Variational Fair Autoencoder
We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible.
Ranked #4 on
Sentiment Analysis
on Multi-Domain Sentiment Dataset
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images.
Scalable Bayesian Optimization Using Deep Neural Networks
Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations.
Ranked #155 on
Image Classification
on CIFAR-100
(using extra training data)
Generative Moment Matching Networks
We consider the problem of learning deep generative models from data.
Learning unbiased features
Different forms of representation learning can be derived from alternative definitions of unwanted bias, e. g., bias to particular tasks, domains, or irrelevant underlying data dimensions.
Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces
In practical Bayesian optimization, we must often search over structures with differing numbers of parameters.
Freeze-Thaw Bayesian Optimization
In this paper we develop a dynamic form of Bayesian optimization for machine learning models with the goal of rapidly finding good hyperparameter settings.
Input Warping for Bayesian Optimization of Non-stationary Functions
Bayesian optimization has proven to be a highly effective methodology for the global optimization of unknown, expensive and multimodal functions.
Multi-Task Bayesian Optimization
We demonstrate the utility of this new acquisition function by utilizing a small dataset in order to explore hyperparameter settings for a large dataset.
Ranked #94 on
Image Classification
on STL-10
Learning Fair Representations
We propose a learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly).
Cardinality Restricted Boltzmann Machines
The Restricted Boltzmann Machine (RBM) is a popular density model that is also good for extracting features.
