arXiv research

Dirac-harmonic maps are uncoupled under certain conditions.

Uncoupled regression is the problem to learn a model from unlabeled data and the set of target values while the correspondence between them is unknown. Such a situation arises in predicting anonymized targets that involve sensitive information, e.g., one's annual income. Since existing methods for uncoupled regression …

Paper establishes identifiability and achievability for causal representation learning.

New algorithms converge faster to Nash equilibrium in zero-sum games with bandit feedback.

Study uncoupled solutions to Dirac-Yang-Mills equations on spin manifolds.

Efficient algorithm converges to Nash equilibrium in bilinear problems with bandit feedback.

New method learns functions without paired data using mediating variables.

Multi-domain translation seeks to learn a probabilistic coupling between marginal distributions that reflects the correspondence between different domains. We assume that data from different domains are generated from a shared latent representation based on a structural equation model. Under this assumption, we show th…

Isotonic regression is a standard problem in shape-constrained estimation where the goal is to estimate an unknown nondecreasing regression function $f$ from independent pairs $(x_i, y_i)$ where $\mathbb{E}[y_i]=f(x_i), i=1, \ldots n$. While this problem is well understood both statistically and computationally, much l…

Node2Grids uncouples GCN training for large graphs, saving memory and computation.

We study Dirac-harmonic maps from surfaces to manifolds with torsion, which is motivated from the superstring action considered in theoretical physics. We discuss analytic and geometric properties of such maps and outline an existence result for uncoupled solutions.

We prove existence results for Dirac-harmonic maps using index theoretical tools. They are mainly interesting if the source manifold has dimension 1 or 2 modulo 8. Our solutions are uncoupled in the sense that the underlying map between the source and target manifolds is a harmonic map.

A new model for simulating cloth manipulation in robots, accurate to within 1cm.

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

First sample-efficient algorithm for learning EFCE in bandit feedback settings.

We classify quasilinear systems in Riemann invariants whose characteristic webs are linearizable on every solution. Although the linearizability of an individual web is a rather nontrivial differential constraint, the requirement of linearizability of characteristic webs on all solutions imposes simple second-order con…

Paper proves existence of Dirac-harmonic maps with trivial index.

In the present report, by using the Stokes-Helmholtz decomposition theorem the 3-dimensional Navier-Stokes equation (NSE) is uncoupled and transformed into a scalar equation for the velocity potential when the flow field is toroidal. The dynamics of the velocity potential is independent of the vector potential. The red…

Agents learn and control complex mechanical systems through shared memories.

The continuous-time random walk (CTRW) is a pure-jump stochastic process with several applications in physics, but also in insurance, finance and economics. A definition is given for a class of stochastic integrals driven by a CTRW, that includes the Ito and Stratonovich cases. An uncoupled CTRW with zero-mean jumps is…

Motivated by the sigma model limit of multicomponent Ginzburg-Landau theory, a version of the Faddeev-Skyrme model is considered in which the scalar field is coupled dynamically to a one-form field called the supercurrent. This coupled model is investigated in the general setting where physical space is an oriented Rie…

We propose a set of convex low rank inducing norms for a coupled matrices and tensors (hereafter coupled tensors), which shares information between matrices and tensors through common modes. More specifically, we propose a mixture of the overlapped trace norm and the latent norms with the matrix trace norm, and then, w…

In this article, we show how the scaling symmetry of the SABR model can be utilized to efficiently price European options. For special kinds of payoffs, the complexity of the problem is reduced by one dimension. For more generic payoffs, instead of solving the 1+2 dimensional SABR PDE, it is sufficient to solve $N_V$ u…

Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.

Smooth calibration improves forecast reliability even with leaked information.

A novel framework for consensus clustering is presented which has the ability to determine both the number of clusters and a final solution using multiple algorithms. A consensus similarity matrix is formed from an ensemble using multiple algorithms and several values for k. A variety of dimension reduction techniques …

We investigate the joint description of the interest-rate term stuctures of Italy and an AAA-rated European country by mean of a --here proposed-- correlated CIR-like bivariate model where one of the state variables is interpreted as a benchmark risk-free rate and the other as a credit spread. The model is constructed …

Defines special Joyce structures for ASK manifolds encoding real HK structures.

UM-GNN improves GNN robustness against poisoning attacks.

New algorithm infers trajectories from partial observations using optimal transport.

Study adversarial classification with data corruption up to ε, deriving geometric flows.

Improved penalty-based methods for bilevel optimization with reduced complexity.

A novel time series imputation technique using tSMOTE for handling missing data.

The paper maps time-series onto networks to reveal hidden joint information.

Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.

Meta-learning improves neural networks by adapting learning algorithms.

Survey explores how transfer learning improves deep reinforcement learning.

New method uses bi-level optimization to learn useful representations for imitation learning.

Study Whittle index learning algorithms for restless bandits with constant stepsizes.

Poisson learning doesn't solve graph semi-supervised learning issues.

New unsupervised learning technique learns independent kernels for better machine learning tasks.

Meta-learning helps models learn quickly from few samples.

New self-imitation learning method improves performance in continuous control tasks.

Deep reinforcement learning finds optimal learning policies for adaptive systems.

Unified framework explains all types of learning, including brain.

Cyclical learning rates improve DRL performance without manual tuning.

Study batch reinforcement learning methods for personalized medical treatments.

A new meta-meta classification method tackles few-shot learning tasks.