paper-with-me

홈 › Papers

Multi-Step Prediction in Linearized Latent State Spaces for Representation Learning

2022-09-02 · A. Tytarenko

In this paper, we derive a novel method as a generalization over LCEs such as E2C. The method develops the idea of learning a locally linear state space, by adding a multi-step prediction, thus allowing for more explicit control over the curvature. We show, that the method outperforms E2C without drastic model changes which come with other works, such as PCC and P3C. We discuss the relation between E2C and the presented method and derived update equations. We provide empirical evidence, which suggests that by considering the multi-step prediction our method - ms-E2C - allows to learn much better latent state spaces in terms of curvature and next state predictability. Finally, we also discuss certain stability challenges we encounter with multi-step predictions and the ways to mitigate them.

📄 PDF Abstract BibTeX arXiv:2209.01127

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Semantic Communication and Control Co-Design for Multi-Objective Correlated Dynamics

2024-10-03 · Abanoub M. Girgis, Hyowoon Seo, Mehdi Bennis

This letter introduces a machine-learning approach to learning the semantic dynamics of correlated systems with different control rules and dynamics. By leveraging the Koopman operator in an autoencoder (AE) framework, t…

Semantic Communication

Sparsifying dimensionality reduction of PDE solution data with Bregman learning

2024-06-18 · Tjeerd Jan Heeringa, Christoph Brune, Mengwu Guo

Classical model reduction techniques project the governing equations onto a linear subspace of the original state space. More recent data-driven techniques use neural networks to enable nonlinear projections. Whilst thos…

compressed sensingDecoderDimensionality Reduction

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory

2023-06-20 · Arnab Kumar Mondal, Siba Smarak Panigrahi, Sai Rajeswar, Kaleem Siddiqi 외

The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could advance Reinforcement Learning (RL) and Planning algorithms, but achieving it is cha…

Reinforcement Learning (RL)

Instance-Level Post Hoc Uncertainty Quantification in Object Detection

2026-06-03 · Chongzhe Zhang, Zifan Zeng, Qunli Zhang, Feng Liu 외 arxiv

Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for safety assurance. Post hoc uncertainty quantification without retraining …

Autonomous DrivingObject Detection

Hierarchical Latent Prediction for Language Models

2026-08-06 · Chang Shi, Tim Pearce, Manan Tomar, Siddhartha Sen 외 arxiv

While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optimal for long-horizon reasoning and planning. Recent works such as Multi-…