Zobrazeno 1 - 10
of 2 689
pro vyhledávání: '"P A Bryon"'
We show that deep neural networks achieve dimension-independent rates of convergence for learning structured densities such as those arising in image, audio, video, and text applications. More precisely, we demonstrate that neural networks with a sim
Externí odkaz:
http://arxiv.org/abs/2411.15095
We consider the linear causal representation learning setting where we observe a linear mixing of $d$ unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent factors as we
Externí odkaz:
http://arxiv.org/abs/2410.24059
Autor:
Aragam, Bryon, Yang, Ruiyi
Multivariate distributions often carry latent structures that are difficult to identify and estimate, and which better reflect the data generating mechanism than extrinsic structures exhibited simply by the raw data. In this paper, we propose a model
Externí odkaz:
http://arxiv.org/abs/2410.22248
We consider the problem of estimating a structured multivariate density, subject to Markov conditions implied by an undirected graph. In the worst case, without Markovian assumptions, this problem suffers from the curse of dimensionality. Our main re
Externí odkaz:
http://arxiv.org/abs/2410.07685
Existing approaches to differentiable structure learning of directed acyclic graphs (DAGs) rely on strong identifiability assumptions in order to guarantee that global minimizers of the acyclicity-constrained optimization problem identifies the true
Externí odkaz:
http://arxiv.org/abs/2410.06163
Quality Diversity (QD) has shown great success in discovering high-performing, diverse policies for robot skill learning. While current benchmarks have led to the development of powerful QD methods, we argue that new paradigms must be developed to fa
Externí odkaz:
http://arxiv.org/abs/2407.17515
Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be easily manipulated by changing contexts, even without altering their fact
Externí odkaz:
http://arxiv.org/abs/2406.18400
Autor:
Aragam, Bryon
One of the hallmark achievements of the theory of graphical models and Bayesian model selection is the celebrated greedy equivalence search (GES) algorithm due to Chickering and Meek. GES is known to consistently estimate the structure of directed ac
Externí odkaz:
http://arxiv.org/abs/2406.17228
Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a simple latent varia
Externí odkaz:
http://arxiv.org/abs/2403.03867
To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build highly-perfo
Externí odkaz:
http://arxiv.org/abs/2402.09236