paper-with-me

Papers

Predicting distributions with Linearizing Belief Networks

2015-11-17 · Yann N. Dauphin, David Grangier

Conditional belief networks introduce stochastic binary variables in neural networks. Contrary to a classical neural network, a belief network can predict more than the expected value of the output $Y$ given the input $X$. It can predict a distribution of outputs $Y$ which is useful when an input can admit multiple outputs whose average is not necessarily a valid answer. Such networks are particularly relevant to inverse problems such as image prediction for denoising, or text to speech. However, traditional sigmoid belief networks are hard to train and are not suited to continuous problems. This work introduces a new family of networks called linearizing belief nets or LBNs. A LBN decomposes into a deep linear network where each linear unit can be turned on or off by non-deterministic binary latent units. It is a universal approximator of real-valued conditional distributions and can be trained using gradient descent. Moreover, the linear pathways efficiently propagate continuous information and they act as multiplicative skip-connections that help optimization by removing gradient diffusion. This yields a model which trains efficiently and improves the state-of-the-art on image denoising and facial expression generation with the Toronto faces dataset.

📄 PDF Abstract BibTeX arXiv:1511.05622

Code (1)

hazdzz/BGU pytorch

Tasks

DenoisingFacial expression generationImage Denoisingtext-to-speechText to Speechvalid

Similar Papers 제목 키워드 기반

GP-SUM. Gaussian Processes Filtering of non-Gaussian Beliefs

2017-09-23 · Maria Bauza, Alberto Rodriguez

This work studies the problem of stochastic dynamic filtering and state propagation with complex beliefs. The main contribution is GP-SUM, a filtering algorithm tailored to dynamic systems and observation models expresse…

AttributeGaussian Processes

The Linearization of Belief Propagation on Pairwise Markov Networks

2015-02-17 · Wolfgang Gatterbauer

Belief Propagation (BP) is a widely used approximation for exact probabilistic inference in graphical models, such as Markov Random Fields (MRFs). In graphs with cycles, however, no exact convergence guarantees for BP ar…

Node Classification

Feedback Linearization for Unknown Systems via Reinforcement Learning

2019-10-29 · Tyler Westenbroek, David Fridovich-Keil, Eric Mazumdar, Shreyas Arora 외

We present a novel approach to control design for nonlinear systems which leverages model-free policy optimization techniques to learn a linearizing controller for a physical plant with unknown dynamics. Feedback lineari…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Feasible Conditional Belief Distributions

2023-07-15 · Itai Arieli, Yakov Babichenko, Fedor Sandomirskiy

Agents receive private signals about an unknown state. The resulting joint belief distributions are complex and lack a simple characterization. Our key insight is that, when conditioned on the state, the structure of bel…

LoLCATs: On Low-Rank Linearizing of Large Language Models

2024-10-14 · Michael Zhang, Simran Arora, Rahul Chalamala, Alan Wu 외

Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretrai…

MMLU