Search Results for author:
Found 19 papers, 14 papers with code
Dataset Distillation
Model distillation aims to distill the knowledge of a complex model into a simpler one.
Dataset Distillation by Matching Training Trajectories
To efficiently obtain the initial and target network parameters for large-scale datasets, we pre-compute and store training trajectories of expert networks trained on the real dataset.
Generalizing Dataset Distillation via Deep Generative Prior
Dataset Distillation aims to distill an entire dataset's knowledge into a few synthetic images.
Rewriting a Deep Generative Model
To address the problem, we propose a formulation in which the desired rule is changed by manipulating a layer of a deep network as a linear associative memory.
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Contrastive representation learning has been outstandingly successful in practice.
Understanding Contrastive Representation Learning through Geometry on the Hypersphere
Contrastive representation learning has been outstandingly successful in practice.
Diverse Image Generation via Self-Conditioned GANs
We introduce a simple but effective unsupervised method for generating realistic and diverse images.
Denoised MDPs: Learning World Models Better Than the World Itself
The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence.
Learning to Synthesize a 4D RGBD Light Field from a Single Image
We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction).
Learning to See by Looking at Noise
We investigate a suite of image generation models that produce images from simple random processes.
On the Learning and Learnability of Quasimetrics
In contrast, our proposed Poisson Quasimetric Embedding (PQE) is the first quasimetric learning formulation that both is learnable with gradient-based optimization and enjoys strong performance guarantees.
Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications.
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
In goal-reaching reinforcement learning (RL), the optimal value function has a particular geometry, called quasimetric structure.
Procedural Image Programs for Representation Learning
Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias.
Meta-Learning MCMC Proposals
The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required.
Totems: Physical Objects for Verifying Visual Integrity
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene.
Steerable Equivariant Representation Learning
In this paper, we propose a method of learning representations that are instead equivariant to data augmentations.
Deep Augmentation: Self-Supervised Learning with Transformations in Activation Space
We use this observation to formulate a method for selecting which layer to target; in particular, our experimentation reveals that targeting deeper layers with Deep Augmentation outperforms augmenting the input data.
