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.
Recent theoretical advances in elasticity of membranes following Helfrich's famous spontaneous curvature model are summarized in this review. The governing equations describing equilibrium configurations of lipid vesicles, lipid membranes with free edges, and chiral lipid membranes are presented. Several analytic solut…
Survey of advances in non-convex min-max optimization for applications.
This paper organizes recent deep learning theory advances.
This paper surveys algorithmic advancements in Optimal Transport with applications in machine learning.
Recent advances in Reinforcement Learning, grounded on combining classical theoretical results with Deep Learning paradigm, led to breakthroughs in many artificial intelligence tasks and gave birth to Deep Reinforcement Learning (DRL) as a field of research. In this work latest DRL algorithms are reviewed with a focus …
Unified theory explains how data augmentation improves deep learning models.
Decision trees improve performance in various fields.
The paper establishes theoretical foundations for low-rank knowledge distillation in LLMs.
Paper improves neural network robustness certification with tighter radii estimates.
Survey on multiplayer bandits, highlighting theoretical gaps and future directions.
Real-world networks usually have community structure, that is, nodes are grouped into densely connected communities. Community detection is one of the most popular and best-studied research topics in network science and has attracted attention in many different fields, including computer science, statistics, social sci…
Survey of deep learning methods for inverse problems, highlighting theoretical challenges.
For a monotonically advancing front, the arrival time is the time when the front reaches a given point. We show that it is twice differentiable everywhere with uniformly bounded second derivative. It is smooth away from the critical points where the equation is degenerate. We also show that the critical set has finite …
Fully Homomorphic Encryption (FHE) refers to a set of encryption schemes that allow computations to be applied directly on encrypted data without requiring a secret key. This enables novel application scenarios where a client can safely offload storage and computation to a third-party cloud provider without having to t…
The book covers scalable MCMC methods for Bayesian learning.
New graph learning model can approximate any function and handle edge values.
High-dimensional statistics advances in complex data domains.
RandNLA uses randomness for matrix problems in machine learning.
Generative method avoids function estimation for data generation.
New method uses dynamic programming for meta continual learning.
These are the lecture notes for an advanced Ph.D. level course I taught in Spring'02 at the C.N. Yang Institute for Theoretical Physics at Stony Brook. The course primarily focused on an introduction to stochastic calculus and derivative pricing with various stochastic computations recast in the language of path integr…
The paper gives picture of enrichment to economic and financial system analysis using agent-based models as a form of advanced study for financial economic data post-statistical-data analysis and micro-simulation analysis. Theoretical exploration is carried out by using comparisons of some usual financial economy syste…
Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning. However, theoretical understanding of their generalization properties and of the manner in which they can assist supervised learning has been lacking. We utilize recent advances in the theory of deep learn…
We prove dual attainment for multi-asset financial derivatives pricing.
In this paper we settle Thurston's old question of whether the Weber-Seifert dodecahedral space is non-Haken, a problem that has been a benchmark for progress in computational 3-manifold topology over recent decades. We resolve this question by combining recent significant advances in normal surface enumeration, new he…
Recent advances in weakly supervised classification allow us to train a classifier only from positive and unlabeled (PU) data. However, existing PU classification methods typically require an accurate estimate of the class-prior probability, which is a critical bottleneck particularly for high-dimensional data. This pr…
EDML is a recently proposed algorithm for learning MAP parameters in Bayesian networks. In this paper, we present a number of new advances and insights on the EDML algorithm. First, we provide the multivalued extension of EDML, originally proposed for Bayesian networks over binary variables. Next, we identify a simplif…
New theory explains how self-supervised learning converges, advancing AI research.
New algorithms improve estimation of treatment effects.
Paper introduces DP methods for high-dimensional variable selection.
We analyze oversquashing in topological message-passing using relational structures.
Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g., the games of Go and Poker, robotics, and autonomous driving, involve the participa…
Survey of AI in finance covering models, strategies, and knowledge systems.
New BO method optimizes functions efficiently even with unknown hyperparameters.
Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully observable environments. In this paper, we generalize a variety of these advances to part…
This thesis tackles NILM challenges with a new dataset and efficient edge deployment techniques.
Study explores learning behavior of GFlowNets, revealing key mechanisms.
We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrain…
FedACS uses attention to select clients with similar data for federated learning.
This study improves scalability of randomized smoothing for certifying classifier robustness.
In this paper, we introduce the first principled adaptive-sampling procedure for learning a convex function in the norm, a problem that arises often in the behavioral and social sciences. We present a function-specific measure of complexity and use it to prove that, for each convex function , our …
Interest prohibition theory concerns theoretical aspects of interest prohibition. We attempt to lay down some aspects of interest prohibition theory wrapped in a larger framework of informal logic. The reason for this is that interest prohibition theory has to deal with a variety of arguments which is so wide that a li…
This dissertation advances the theoretical foundation of local optimization methods in Federated Learning.
Recent advances in deep learning theory have evoked the study of generalizability across different local minima of deep neural networks (DNNs). While current work focused on either discovering properties of good local minima or developing regularization techniques to induce good local minima, no approach exists that ca…
Bayesian optimisation has gained great popularity as a tool for optimising the parameters of machine learning algorithms and models. Somewhat ironically, setting up the hyper-parameters of Bayesian optimisation methods is notoriously hard. While reasonable practical solutions have been advanced, they can often fail to …
Measures time-delay embedding for noisy, sparse data.
We analyze GANs using neural tangent kernels, revealing flaws and advancing understanding.
We in this paper propose a realizable framework TECU, which embeds task-specific strategies into update schemes of coordinate descent, for optimizing multivariate non-convex problems with coupled objective functions. On one hand, TECU is capable of improving algorithm efficiencies through embedding productive numerical…