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.
Classifies when homeomorphism groups of stable surfaces have automatic continuity.
Let M be a compact manifold, possibly with boundary. We show that the group of homeomorphisms of M has the automatic continuity property: any homomorphism from Homeo(M) to any separable group is necessarily continuous. This answers a question of C. Rosendal. If N is a submanifold of M, the group of homeomorphisms of M …
Extends continuity proof to non-compact manifolds and groups.
Paper introduces new estimator for continuous treatment effects.
Classifies surfaces for pure mapping class groups with automatic continuity.
Automatic continuity of polynomial maps and cocycles proved.
Automatically adjusts model size for continual Gaussian processes.
We show that any homomorphism from the homeomorphism group of a compact 2-manifold, with the compact-open topology, or equivalently, with the topology of uniform convergence, into a separable topological group is automatically continuous.
Study Hamiltonian diffeomorphisms on symplectic manifolds and properties of invariant convex functions.
This paper proposes a method to safely adjust exploration in RL to satisfy constraints.
This paper introduces a general Bayesian non- parametric latent feature model suitable to per- form automatic exploratory analysis of heterogeneous datasets, where the attributes describing each object can be either discrete, continuous or mixed variables. The proposed model presents several important properties. First…
The paper characterizes risk measures with the Fatou property in function spaces.
Lie groupoids and their associated algebroids arise naturally in the study of the constitutive properties of continuous media. Thus, Continuum Mechanics and Differential Geometry illuminate each other in a mutual entanglement of theory and applications. Given any material property, such as the elastic energy or an inde…
CL methods improve monolingual ASR models across new tasks without forgetting past data.
In this note we derive the backward (automatic) differentiation (adjoint [automatic] differentiation) for an algorithm containing a conditional expectation operator. As an example we consider the backward algorithm as it is used in Bermudan product valuation, but the method is applicable in full generality. The method …
The study explores homeomorphism groups of self-similar 2-manifolds, including the 2-sphere and Cantor set.
The theory of automatic groups is developed, including properties and practical algorithms.
Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor overhead in terms of interactions in the environment. To achieve this, we combine Neur…
Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference. We propose a novel framework for understanding multiplicative noise in neural net…
Perfect mapping class groups of specific surfaces have no proper subgroups.
In this paper we investigate whether electroencephalography (EEG) features can be used to improve the performance of continuous visual speech recognition systems. We implemented a connectionist temporal classification (CTC) based end-to-end automatic speech recognition (ASR) model for performing recognition. Our result…
Minimal topology on surface homeomorphisms proven.
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in compl…
This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and …
Improves risk and variability measures continuity and consistency.
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent…
Procedure groups nonparametric regression curves automatically.
Study shows compact mapping class groups of infinite type surfaces are never perfect.
In this paper we explore continuous silent speech recognition using electroencephalography (EEG) signals. We implemented a connectionist temporal classification (CTC) automatic speech recognition (ASR) model to translate EEG signals recorded in parallel while subjects were reading English sentences in their mind withou…
Identifies a gradient flow to solve kernel learning problems with noise reduction.
The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enables for proper random generation of hidden unit parameters advancing conventional randomized approaches constrained with a fixed scope of rand…
Study presentations of groups that can be generalised over continuous open group monomorphisms.
Automatic debiasing for causal and policy effects using Neural Nets and Random Forests.
Groups with specific curvature have a regular language of geodesics.
Making sense of a dataset in an automatic and unsupervised fashion is a challenging problem in statistics and AI. Classical approaches for {exploratory data analysis} are usually not flexible enough to deal with the uncertainty inherent to real-world data: they are often restricted to fixed latent interaction models an…
This paper introduces a new reward shaping method for average-reward reinforcement learning.
We place an Indian Buffet process (IBP) prior over the structure of a Bayesian Neural Network (BNN), thus allowing the complexity of the BNN to increase and decrease automatically. We further extend this model such that the prior on the structure of each hidden layer is shared globally across all layers, using a Hierar…
Automates GNN design for molecular property prediction.
Latent feature modeling allows capturing the latent structure responsible for generating the observed properties of a set of objects. It is often used to make predictions either for new values of interest or missing information in the original data, as well as to perform data exploratory analysis. However, although the…
New algorithm selects variables from large datasets.
New algorithm improves causal effect estimation for continuous treatments.
In this paper we investigate continuous speech recognition using electroencephalography (EEG) features using recently introduced end-to-end transformer based automatic speech recognition (ASR) model. Our results demonstrate that transformer based model demonstrate faster training compared to recurrent neural network (R…
A method for setting up an automatic curriculum for reinforcement learning tasks.
Automatically differentiable estimation for BLP model reduces bias in demand estimation.
Notes on continuity of discrete-spectrum Fredholm operators.
Extracts important peaks from XRD spectra using Attention mechanism.
Proves properties of sub-Riemannian exponential map, showing it's not injective.
Automatic neural architecture design has shown its potential in discovering powerful neural network architectures. Existing methods, no matter based on reinforcement learning or evolutionary algorithms (EA), conduct architecture search in a discrete space, which is highly inefficient. In this paper, we propose a simple…