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.
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments. To do so, we study how a teacher algorithm can learn to generate a learning curriculum, whereby it sequentially samples parameters contr…
Framework improves agent's ability to learn from noisy images.
Model predicts cannabis use disorder risk for adolescents and young adults.
Nonlinearity is crucial to the performance of a deep (neural) network (DN). To date there has been little progress understanding the menagerie of available nonlinearities, but recently progress has been made on understanding the rôle played by piecewise affine and convex nonlinearities like the ReLU and absolute value …
Progress in probabilistic generative models has accelerated, developing richer models with neural architectures, implicit densities, and with scalable algorithms for their Bayesian inference. However, there has been limited progress in models that capture causal relationships, for example, how individual genetic factor…
Research connects probabilistic and variational approaches to Kahler-Einstein metrics.
Hypothesis testing is an important cognitive process that supports human reasoning. In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks. Our approach involves a hypothesis testing loop that reconsiders and progressively refines a previously formed hypothesis…
Paper introduces a new curriculum generation method for reinforcement learning.
Disease progression modeling (DPM) using longitudinal data is a challenging machine learning task. Existing DPM algorithms neglect temporal dependencies among measurements, make parametric assumptions about biomarker trajectories, do not model multiple biomarkers jointly, and need an alignment of subjects' trajectories…
This paper improves disentanglement in VAEs by progressively learning hierarchical representations.
New algorithm outperforms existing ones by focusing on mastering rate.
Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks. We see a striking…
Develops a privacy-preserving algorithm for sparse robust regression.
This work designs an active world model learning system with progress-based curiosity.
Deep learning's success requires vast computing power, making future progress unsustainable.
Study uses machine learning and survival analysis to predict CKD progression.
Study finds little progress in medical machine learning benchmarks over 3 years.
We study grassmannians associated with a linear space with a nondegenerate hermitian form. The geometry of these grassmannians allows us to explain the relation between a (pseudo-)riemannian projective geometry and the conformal structure on its ideal boundary (absolute). Such relation encompasses, for instance, the us…
New 4-manifolds with exotic diffeomorphisms found.
The paper bounds the mean absolute error in DNN vector-to-vector regression.
Alzheimer's disease (AD) is a degenerative brain disease impairing a person's ability to perform day to day activities. The clinical manifestations of Alzheimer's disease are characterized by heterogeneity in age, disease span, progression rate, impairment of memory and cognitive abilities. Due to these variabilities, …
We introduce a novel approach for predicting the progression of adolescent idiopathic scoliosis from 3D spine models reconstructed from biplanar X-ray images. Recent progress in machine learning have allowed to improve classification and prognosis rates, but lack a probabilistic framework to measure uncertainty in the …
Combines absolute and relative wealth in portfolio optimization with power utility functions.
Improved self-supervised learning on ImageNet achieves top-1 accuracy of 77.1%.
A complete surface of constant mean curvature 1 (CMC-1) in hyperbolic 3-space with constant curvature -1 has two natural notions of "total curvature"-- one is the total absolute curvature which is the integral over the surface of the absolute value of the Gaussian curvature, and the other is the dual total absolute cur…
Curriculum learning speeds up agent learning in Minecraft, a complex visual domain.
Absolutely partially hyperbolic surface endomorphisms have a coherent center foliation.
The paper introduces Absolute Shapley Value to handle negative contributions in machine learning model training.
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is a…
Deep neural nets on 1-D data are convex Lasso models with reflection features.
Study absolute equivalence for Pfaffian systems, applying to control systems.
Neural networks learn distance-based representations, not just intensity.
The paper studies curves in Finsler-like spaces and their properties.
Researchers compute Bayes error for classification models using normalizing flows.
The aim of the present paper is to investigate conformal changes in absolute parallelism geometry. We find out some new conformal invariants in terms of the Weitzenböck connection and the Levi-Civita connection of an absolute parallelism space.
LALR adapts learning rate for faster convergence in regression and neural nets.
New method predicts AD progression using MEG brain networks.
This paper extends results of Mortimer and Williams (1991) about changes of probability measure up to a random time under the assumptions that all martingales are continuous and that the random time avoids stopping times. We consider locally absolutely continuous measure changes up to a random time, changes of probabil…
Bayesian model identifies health disparities in disease progression.
A classical result in Riemannian geometry states that the absolutely continuous curves into a (finite-dimensional) Riemannian manifold form an infinite-dimensional manifold. In the present paper this construction and related results are generalised to absolutely continuous curves with values in a strong Riemannian mani…
Study absolute continuity of Wasserstein barycenters on manifolds with singular cost functions.
Deep neural networks solve Raven's Progressive Matrices with high accuracy.
We show how to construct absolutely exotic smooth structures on compact 4-manifolds with boundary, including contractible manifolds. In particular, we prove that any compact smooth 4-manifold W with boundary that admits a relatively exotic structure contains a pair of codimension-zero submanifolds homotopy equivalent t…
Gradient span algorithms show consistent progress in high dimensions.
We prove that any isometry between the unit spheres of -smooth (more generally, absolutely smooth) smooth Banach spaces extends to a linear isometry of the Banach spaces. This answers the famous Tingley's problem in the class of absolutely smooth -dimensional Banach spaces.
In a recent joint work with V. Turaev (cf. math.DG/9810114) we defined a new concept of combinatorial torsion which we called absolute torsion. Compared with the classical Reidemeister torsion it has the advantage of having a well-defined sign. Also, the absolute torsion is defined for arbitrary orientable flat vector …
Proposes a new Huber loss combining absolute and quadratic properties.
A compactum X is an `absolute cone' if, for each of its points x, the space X is homeomorphic to a cone with x corresponding to the cone point. In 1971, J. de Groot conjectured that each n-dimensional absolute cone is an n-cell. In this paper, we give a complete solution to that conjecture. In particular, we show that …