Search Results for author:
Found 22 papers, 6 papers with code
Language Modeling Is Compression
We show that large language models are powerful general-purpose predictors and that the compression viewpoint provides novel insights into scaling laws, tokenization, and in-context learning.
Randomized Positional Encodings Boost Length Generalization of Transformers
Transformers have impressive generalization capabilities on tasks with a fixed context length.
Memory-Based Meta-Learning on Non-Stationary Distributions
Memory-based meta-learning is a technique for approximating Bayes-optimal predictors.
Beyond Bayes-optimality: meta-learning what you know you don't know
This is in contrast to risk-sensitive agents, which additionally exploit the higher-order moments of the return, and ambiguity-sensitive agents, which act differently when recognizing situations in which they lack knowledge.
Neural Networks and the Chomsky Hierarchy
Reliable generalization lies at the heart of safe ML and AI.
Your Policy Regularizer is Secretly an Adversary
Policy regularization methods such as maximum entropy regularization are widely used in reinforcement learning to improve the robustness of a learned policy.
Model-Free Risk-Sensitive Reinforcement Learning
Since the Gaussian free energy is known to be a certainty-equivalent sensitive to the mean and the variance, the learning rule has applications in risk-sensitive decision-making.
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains.
Stochastic Approximation of Gaussian Free Energy for Risk-Sensitive Reinforcement Learning
Since the Gaussian free energy is known to be a certainty-equivalent sensitive to the mean and the variance, the learning rule has applications in risk-sensitive decision-making.
Causal Analysis of Agent Behavior for AI Safety
As machine learning systems become more powerful they also become increasingly unpredictable and opaque.
Algorithms for Causal Reasoning in Probability Trees
Probability trees are one of the simplest models of causal generative processes.
Meta-trained agents implement Bayes-optimal agents
Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution.
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
Sinkhorn AutoEncoders
We show that minimizing the p-Wasserstein distance between the generator and the true data distribution is equivalent to the unconstrained min-min optimization of the p-Wasserstein distance between the encoder aggregated posterior and the prior in latent space, plus a reconstruction error.
The Power of Ensembles for Active Learning in Image Classification
To investigate why Monte-Carlo Dropout uncertainties perform worse, we explore potential differences in isolation in a series of experiments.
An information-theoretic on-line update principle for perception-action coupling
Here we consider perception and action as two serial information channels with limited information-processing capacity.
Variational Network Quantization
In this paper, the preparation of a neural network for pruning and few-bit quantization is formulated as a variational inference problem.
On Detecting Adversarial Perturbations
In this work, we propose to augment deep neural networks with a small "detector" subnetwork which is trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations.
Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes
As limit cases, this generalized scheme includes standard value iteration with a known model, Bayesian MDP planning, and robust planning.
Abstraction in decision-makers with limited information processing capabilities
A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise.
A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function
We propose a novel Bayesian approach to solve stochastic optimization problems that involve finding extrema of noisy, nonlinear functions.
