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.
This paper shows how path spaces on two-level manifolds can be Hilbert manifold structures.
Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we present a new theoretical framework for analyzing over-parameterized neural networks …
This work analyzes generalization in federated learning using information theory.
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 …
Fast BATLLNN speeds up verification of TLL NNs by 400x.
Develops a two-level monotonic multistage recommender system for better user-specific prediction.
This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.
LARF improves random forests with attention mechanisms and contamination models.
Paper develops efficient algorithms for robust optimization across multiple groups.
New NN design for nonlinear systems control with guarantees.
In Maslov (2003), a two level model of the occurrence of financial pyramid (bubbles) has been considered. We also considered the mathematical analogy of this model to Bose condensation. In the present paper, we explain why Ponzi schemes and bubbles result in a crisis in real economics. In Maslov (2005), the law of incr…
OKDDip uses diverse peers to improve online knowledge distillation.
We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution. To incentivise an informative latent representation of the data, we formulate the learning problem as a constrained optimisation problem by extending …
This paper examines the valuation of American capped call options with two-level caps. The structure of the immediate exercise region is significantly more complex than in the classical case with constant cap. When the cap grows over time, making extensive use of probabilistic arguments and local time, we show that the…
Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that , , or algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on predi…
We study the quantum synchronization between a pair of two-level systems inside two coupled cavities. By using a digital-analog decomposition of the master equation that rules the system dynamics, we show that this approach leads to quantum synchronization between both two-level systems. Moreover, we can identify in th…
Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinfor…
A new method predicts stock ranking uncertainty to improve trading performance during regime shifts.
The stochastic variational inference (SVI) paradigm, which combines variational inference, natural gradients, and stochastic updates, was recently proposed for large-scale data analysis in conjugate Bayesian models and demonstrated to be effective in several problems. This paper studies a family of Bayesian latent vari…
To answer the existence of optimal swimmer learning/teaching strategies, this work introduces a two-level clustering in order to analyze temporal dynamics of motor learning in breaststroke swimming. Each level have been performed through Sparse Fisher-EM, a unsupervised framework which can be applied efficiently on lar…
A2SGD reduces distributed SGD communication to O(1) per worker.
The paper designs neural networks with assurance for controlling nonlinear systems.
Paper explores generalization of AID-based bi-level optimization methods.
This paper shows overparameterized deep neural networks are convex and learn useful features.
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms, models, operators, or numerical systems threaten the viability of specialized hardware…
Polynomial-time reachability for LTI systems with TLL NN controllers is achieved.
MCCE generates realistic counterfactual explanations for tabular data.
New autoencoder uses goodness-of-fit tests for better model performance.
Proposes a method for explaining black-box models with nested feature attributions.
A theorem connects integral of second-order derivatives to function rise.
GraphHull models networks with clear multi-scale explanations of community structure.
HyperSAGE learns node representations in hypergraphs without losing information.
New method controls linear systems with partial info and disturbances.
This paper deals with prediction of anopheles number, the main vector of malaria risk, using environmental and climate variables. The variables selection is based on an automatic machine learning method using regression trees, and random forests combined with stratified two levels cross validation. The minimum threshol…
Proposes GST for efficient computation of generalized Sobolev transport on graph metrics.
Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitiv…
The main results of this paper consists of two parts. Firstly, we obtain an almost rigidity theorem which says that on a RCD(0, N) space, when a domain between two level sets of a distance function has almost maximal volume compared to that of a cylinder, then this portion is close to a cylinder as a metric space. Seco…
We study the isoperimetric, functional and concentration properties of -dimensional weighted Riemannian manifolds satisfying the Curvature-Dimension condition, when the generalized dimension is negative, and more generally, is in the range , extending the scope from the traditional range $N \i…
We study a two-level multiview learning with more than two views under the PAC-Bayesian framework. This approach, sometimes referred as late fusion, consists in learning sequentially multiple view-specific classifiers at the first level, and then combining these view-specific classifiers at the second level. Our main t…
Emotions play a crucial role in human interaction, health care and security investigations and monitoring. Automatic emotion recognition (AER) using electroencephalogram (EEG) signals is an effective method for decoding the real emotions, which are independent of body gestures, but it is a challenging problem. Several …
This work analyzes Gibbs samplers for Bayesian hierarchical models without dimensionality constraints.
The quantum navigation problem of finding the time-optimal control Hamiltonian that transports a given initial state to a target state through quantum wind, that is, under the influence of external fields or potentials, is analysed. By lifting the problem from the state space to the space of unitary gates realising the…
Anomaly detection is the process of finding data points that deviate from a baseline. In a real-life setting, anomalies are usually unknown or extremely rare. Moreover, the detection must be accomplished in a timely manner or the risk of corrupting the system might grow exponentially. In this work, we propose a two lev…
The study predicts bankruptcy in Indian companies using financial ratios.
This paper is the continuation of "Pricing with coherent risk" and deals with further applications of coherent risk measures to problems of finance. First, we study the optimization problem. Three forms of this problem are considered. Furthermore, the results obtained are applied to the optimality pricing. Again three …
Taxonomies of cryptocurrencies and comparisons with fiat money and databases.
In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple cooperative critics from two levels of the hierarchy and propose a reinforcement learnin…
Recently ({\em Class. Quant. Grav.} {\bf 20} 625-664) the concept of {\em causal mapping} between spacetimes --essentially equivalent in this context to the {\em chronological map} one in abstract chronological spaces--, and the related notion of {\em causal structure}, have been introduced as new tools to study causal…