A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Generative models use latent abstractions to create images.
Algorithm finds latent structure in value functions for improved reinforcement learning.
Proposes method to learn state abstractions that generalize across environments.
A method uses RL to learn abstractions for planning, improving robot navigation and manipulation tasks.
New framework identifies causal models with arbitrary interventions, improving realism.
We present an encoder-powered generative adversarial network (EncGAN) that is able to learn both the multi-manifold structure and the abstract features of data. Unlike the conventional decoder-based GANs, EncGAN uses an encoder to model the manifold structure and invert the encoder to generate data. This unique scheme …
TASID learns policies in high-dimensional settings with abstract simulator knowledge.
Math theory explains how neural networks learn abstract representations.
This study analyzes data science vocabulary changes over 13 years.
Develops SCMs for latent selection to simplify causal analysis.
We present an algorithm, HOMER, for exploration and reinforcement learning in rich observation environments that are summarizable by an unknown latent state space. The algorithm interleaves representation learning to identify a new notion of kinematic state abstraction with strategic exploration to reach new states usi…
Steady progress has been made in abstractive summarization with attention-based sequence-to-sequence learning models. In this paper, we propose a new decoder where the output summary is generated by conditioning on both the input text and the latent topics of the document. The latent topics, identified by a topic model…
In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive Matrices. We show that the latent representations, learned by unsupervised training …
In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We sho…
In this paper, we implement an information-theoretic approach to travel behaviour analysis by introducing a generative modelling framework to identify informative latent characteristics in travel decision making. It involves developing a joint tri-partite Bayesian graphical network model using a Restricted Boltzmann Ma…
Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…
Latent features learned by deep learning approaches have proven to be a powerful tool for machine learning. They serve as a data abstraction that makes learning easier by capturing regularities in data explicitly. Their benefits motivated their adaptation to relational learning context. In our previous work, we introdu…
A new estimator reduces variance in slate bandit OPE.
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state …
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and temporal modeling. The arch…
Paper develops a framework to identify latent dynamics from high-dimensional data.
This work extends HiP-MDPs to robust state abstractions for multi-task and meta-reinforcement learning.
We present LumièreNet, a simple, modular, and completely deep-learning based architecture that synthesizes, high quality, full-pose headshot lecture videos from instructor's new audio narration of any length. Unlike prior works, LumièreNet is entirely composed of trainable neural network modules to learn mapping functi…
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
Optimus pre-trains sentences in a latent space for various NLP tasks.
Formalizes concepts as latent variables in hierarchical models for high-dimensional data.
CompVAE handles multi-ensemble data with compositional generative model.
Mid-training improves RL by identifying compact action abstractions.
Paper learns meaningful state and action representations from MDP trajectories.
This work uses action equivariance to learn structured latent spaces for reinforcement learning.
A new method measures heterogeneity without needing categorical partitioning or distance measurement.
A new method for math reasoning that allows for iterative correction.
SuTaT creates dialogue summaries for tete-a-tetes without labeled data.
Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however, despite several recent improvements, the training of discrete latent variable m…
Learning attribute applicability of products in the Amazon catalog (e.g., predicting that a shoe should have a value for size, but not for battery-type at scale is a challenge. The need for an interpretable model is contingent on (1) the lack of ground truth training data, (2) the need to utilise prior information abou…
This work explains how linear representations in large language models arise from training objectives and gradient descent.
New findings show disentangled latent representations are not enough for robust compositional generalization.
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP layers to learn abstract representations of the state feature space, which is link…
VQShape learns interpretable time-series representations and achieves comparable performance to specialist models.
Interprets how intrinsic motivation shapes behavior in RL agents.
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit in generalizing to physical tasks in a combinatorial space the learner has not encountered before. We present object-centric perception, pred…
SG-NTF completes HDI tensors with spectral mapping and spatio-temporal gating.
This work discovers latent field effects governing interacting dynamical systems.
A network supporting deep unsupervised learning is presented. The network is an autoencoder with lateral shortcut connections from the encoder to decoder at each level of the hierarchy. The lateral shortcut connections allow the higher levels of the hierarchy to focus on abstract invariant features. While standard auto…
Proves efficient learning of hierarchical structure in meta-reinforcement learning.
This paper introduces the probabilistic module interface, which allows encapsulation of complex probabilistic models with latent variables alongside custom stochastic approximate inference machinery, and provides a platform-agnostic abstraction barrier separating the model internals from the host probabilistic inferenc…
We introduce a method to learn a hierarchy of successively more abstract representations of complex data based on optimizing an information-theoretic objective. Intuitively, the optimization searches for a set of latent factors that best explain the correlations in the data as measured by multivariate mutual informatio…
Analogy-making is a key method for computer algorithms to generate both natural and creative music pieces. In general, an analogy is made by partially transferring the music abstractions, i.e., high-level representations and their relationships, from one piece to another; however, this procedure requires disentangling …