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.
Model learns disentangled object location and appearance representations.
Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that…
OBSER framework infers sub-environments from objects, outperforming scene-based methods.
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…
A method to prevent image representation collapse through data-dependent augmentation.
Enhances RL agents with predictive internal representations.
Object-based factorizations provide a useful level of abstraction for interacting with the world. Building explicit object representations, however, often requires supervisory signals that are difficult to obtain in practice. We present a paradigm for learning object-centric representations for physical scene understan…
Geographic object-based image analysis (GEOBIA) framework has gained increasing interest recently. Following this popular paradigm, we propose a novel multiscale classification approach operating on a hierarchical image representation built from two images at different resolutions. They capture the same scene with diff…
C-SWMs learn structured world models from raw data.
This paper tackles fairness in PCA by balancing it with reconstruction error.
New unsupervised learning framework for sound recognition.
New method improves domain generalization by matching object representations.
Designs a framework to transfer causal models between similar environments.
In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to each observation which is then modified by applying the domain specific transforma…
The paper introduces a new metric to quantify uncertainty's impact on multiple objectives.
Self-Predictive Representations improves data-efficient reinforcement learning from limited interaction.
Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning. In this work, we…
New method embeds bipartite graphs into vectors, overcoming nonlinear challenges.
Self-supervised learning excels in topic modeling by being less model-specific.
Forward-prediction models enhance physical reasoning, but only for specific tasks.
New model separates objects in scenes, enabling novel arrangements and depth.
A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disent…
Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we present an algorithm for learning object models of non-stationary objects found in office-type environments. Our algorithm exp…
New algorithm B++&C improves hierarchical clustering on large deep embedding datasets.
Inverse braid monoid describes a structure on braids where the number of strings is not fixed. So, some strings of initial may be deleted. In the paper we show that many properties and objects based on braid groups may be extended to the inverse braid monoids. Namely we prove an inclusion into a monoid of partial m…
Classifies spherical objects filled with water or air using acoustic echoes and Form Function.
Bayesian model for multi-environment prediction with latent variable changes.
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules. We consider rules in both conjunctive normal form (AND-of-ORs) and disjunctive normal form (OR-of-ANDs). A principled objective function is proposed to trade …
A faster algorithm for ranking from pairwise comparisons.
We propose a deep learning approach for discovering kernels tailored to identifying clusters over sample data. Our neural network produces sample embeddings that are motivated by--and are at least as expressive as--spectral clustering. Our training objective, based on the Hilbert Schmidt Information Criterion, can be o…
Deep learning solves complex stochastic control with jumps.
New approach to extremal hyperbolic surfaces using NEC groups.
Study non-Weinstein Liouville geometry via hyperbolic dynamics, proving rigidity results.
We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the same time is trained to map the true data distribution to the prior in latent spac…
Machine learning models classify celestial objects like pulsars and black holes.
The task of clustering a set of objects based on multiple sources of data arises in several modern applications. We propose an integrative statistical model that permits a separate clustering of the objects for each data source. These separate clusterings adhere loosely to an overall consensus clustering, and hence the…
Text style transfer aims to modify the style of a sentence while keeping its content unchanged. Recent style transfer systems often fail to faithfully preserve the content after changing the style. This paper proposes a structured content preserving model that leverages linguistic information in the structured fine-gra…
New method uses batch normalization to improve OoD detection.
New computational methods improve clustering of objects.
Building on a specific formalization of analogical relationships of the form "A relates to B as C relates to D", we establish a connection between two important subfields of artificial intelligence, namely analogical reasoning and kernel-based machine learning. More specifically, we show that so-called analogical propo…
In this work, we study a new approach to optimizing the margin distribution realized by binary classifiers. The classical approach to this problem is simply maximization of the expected margin, while more recent proposals consider simultaneous variance control and proxy objectives based on robust location estimates, in…
New framework embeds physics in coarse-grained models without big data.
Paper proposes an end-to-end learning method for state estimation in robotics.
Proposes new loss functions for GANs to improve estimation accuracy and robustness.
Ensuring that classifiers are non-discriminatory or fair with respect to a sensitive feature (e.g., race or gender) is a topical problem. Progress in this task requires fixing a definition of fairness, and there have been several proposals in this regard over the past few years. Several of these, however, assume either…
The morphological structure of left ventricle segmented from cardiac magnetic resonance images can be used to calculate key clinical parameters, and it is of great significance to the accurate and efficient diagnosis of cardiovascular diseases. Compared with traditional methods, the segmentation algorithms based on ful…
New algorithms optimize non-smooth, non-convex objectives with improved complexity.
Obtaining labels can be costly and time-consuming. Active learning allows a learning algorithm to intelligently query samples to be labeled for efficient learning. Fisher information ratio (FIR) has been used as an objective for selecting queries in active learning. However, little is known about the theory behind the …