Search Results for author:
Found 32 papers, 13 papers with code
Evolving Deeper LLM Thinking
We explore an evolutionary search strategy for scaling inference time compute in Large Language Models.
Stochastic Sampling from Deterministic Flow Models
Deterministic flow models, such as rectified flows, offer a general framework for learning a deterministic transport map between two distributions, realized as the vector field for an ordinary differential equation (ODE).
A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs.
Weighted Ensemble Self-Supervised Learning
Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning.
PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale
The predictive information, the mutual information between the past and future, has been shown to be a useful representation learning auxiliary loss for training reinforcement learning agents, as the ability to model what will happen next is critical to success on many control tasks.
Deep Hierarchical Planning from Pixels
Despite operating in latent space, the decisions are interpretable because the world model can decode goals into images for visualization.
Multi-Game Decision Transformers
Specifically, we show that a single transformer-based model - with a single set of weights - trained purely offline can play a suite of up to 46 Atari games simultaneously at close-to-human performance.
An Empirical Investigation of Representation Learning for Imitation
We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation across several environment suites.
Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck
In addition, it provides a mechanism for learning a joint distribution of the latent variable and the sparsity and hence can account for the complete uncertainty in the latent space.
Compressive Visual Representations
We verify this by developing SimCLR and BYOL formulations compatible with the Conditional Entropy Bottleneck (CEB) objective, allowing us to both measure and control the amount of compression in the learned representation, and observe their impact on downstream tasks.
Ranked #41 on
Self-Supervised Image Classification
on ImageNet
VIB is Half Bayes
In discriminative settings such as regression and classification there are two random variables at play, the inputs X and the targets Y.
Predictive Information Accelerates Learning in RL
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future).
Cycles in Causal Learning
In the causal learning setting, we wish to learn cause-and-effect relationships between variables such that we can correctly infer the effect of an intervention.
An Unsupervised Information-Theoretic Perceptual Quality Metric
We show that PIM is competitive with supervised metrics on the recent and challenging BAPPS image quality assessment dataset and outperforms them in predicting the ranking of image compression methods in CLIC 2020.
CEB Improves Model Robustness
We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve model robustness.
The Conditional Entropy Bottleneck
We experimentally test our hypothesis by comparing the performance of CEB models with deterministic models and Variational Information Bottleneck (VIB) models on a variety of different datasets and robustness challenges.
Phase Transitions for the Information Bottleneck in Representation Learning
In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the dataset and the learned representation?
Information-Bottleneck Approach to Salient Region Discovery
We propose a new method for learning image attention masks in a semi-supervised setting based on the Information Bottleneck principle.
Learnability for the Information Bottleneck
However, in practice, not only is $\beta$ chosen empirically without theoretical guidance, there is also a lack of theoretical understanding between $\beta$, learnability, the intrinsic nature of the dataset and model capacity.
Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces
Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information.
Learning Latent Dynamics for Planning from Pixels
Planning has been very successful for control tasks with known environment dynamics.
Ranked #2 on
Continuous Control
on DeepMind Walker Walk (Images)
TherML: The Thermodynamics of Machine Learning
In this work we offer an information-theoretic framework for representation learning that connects with a wide class of existing objectives in machine learning.
TherML: Thermodynamics of Machine Learning
In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning.
Uncertainty in the Variational Information Bottleneck
We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data.
GILBO: One Metric to Measure Them All
We propose a simple, tractable lower bound on the mutual information contained in the joint generative density of any latent variable generative model: the GILBO (Generative Information Lower BOund).
An information-theoretic analysis of deep latent-variable models
We present an information-theoretic framework for understanding trade-offs in unsupervised learning of deep latent-variables models using variational inference.
Fixing a Broken ELBO
Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models.
Generative Models of Visually Grounded Imagination
It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before.
Adversarial Transformation Networks: Learning to Generate Adversarial Examples
We efficiently train feed-forward neural networks in a self-supervised manner to generate adversarial examples against a target network or set of networks.
Adversarial examples for generative models
We explore methods of producing adversarial examples on deep generative models such as the variational autoencoder (VAE) and the VAE-GAN.
Deep Variational Information Bottleneck
We present a variational approximation to the information bottleneck of Tishby et al. (1999).
Speed/accuracy trade-offs for modern convolutional object detectors
On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
Ranked #226 on
Object Detection
on COCO test-dev
(using extra training data)
