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 research improves binary classification by balancing overfitting and generalization with a novel Bayesian approach.
Hopf's Umlaufsatz relates the total curvature of a closed immersed plane curve to its rotation number. While the curvature of a curve changes under local deformations, its integral over a closed curve is invariant under regular homotopies. A natural question is whether one can find some non-trivial densities on a curve…
We show that the EH class and the LOSS invariant of Legendrian knots in contact 3-manifolds are functorial under regular Lagrangian concordances in Weinstein cobordisms. This gives computable obstructions to the existence of regular Lagrangian concordances.
Study reveals learning curves and benign overfitting in spectral algorithms for large dimensions.
The paper reveals three mechanisms for weak-to-strong generalization.
The sparse representation classifier (SRC) is shown to work well for image recognition problems that satisfy a subspace assumption. In this paper we propose a new implementation of SRC via screening, establish its equivalence to the original SRC under regularity conditions, and prove its classification consistency for …
The sparse representation classifier (SRC) has been utilized in various classification problems, which makes use of L1 minimization and works well for image recognition satisfying a subspace assumption. In this paper we propose a new implementation of SRC via screening, establish its equivalence to the original SRC und…
A bounded curvature path is a continuously differentiable piecewise path with a bounded absolute curvature that connects two points in the tangent bundle of a surface. In this work, we analyze the homotopy classes of bounded curvature paths for points in the tangent bundle of the Euclidean plane. We show the exis…
We consider properties of the total absolute geodesic curvature functional on circle immersions into a Riemann surface. In particular, we study its behavior under regular homotopies, its infima in regular homotopy classes, and the homotopy types of spaces of its local minima. We consider properties of the total curvatu…
Kim-Milman flow map stable under regular target measures
We investigate manifolds obtained as a quotient of a doubly warped product. We show that they are always covered by the product of two suitable leaves. This allows us to prove, under regularity hypothesis, that these manifolds are a doubly warped product up to a zero measure subset formed by an union of leaves. We also…
Unified framework for shrinkage, thresholding, and regularization in normal mean estimation and linear regression.
Solvable structures, likewise solvable algebras of local symmetries, can be used to integrate scalar ODEs by quadratures. Solvable structures, however, are particularly suitable for the integration of ODEs with a lack of local symmetries. In fact, under regularity assumptions, any given ODE always admits solvable struc…
The paper bounds the complexity of GCNs using Rademacher complexity.
Study shows -NN regressor consistency in complex survey designs.
Invariant detects triple points in sphere immersions.
New method uses fractional posteriors for semiparametric inference with improved uncertainty quantification.
Consider the standard symplectic $(\RR^{2n}, ω_0)$, a point $p\in\RR^{2n}$ and an immersed closed orientable hypersurface $Σ\subset\RR^{2n}\minus\{p\}$, all in general position. We study the following passage/tangency question: how many lines in $\RR^{2n}$ pass through and tangent to parallel to the 1-dimension…
Paper introduces a neural network for consistent estimation of optimal transport maps.
The universal Liouville action equals the renormalized volume of a hyperbolic 3-manifold.
We analyze MDL for binary classification, quantifying overfitting and underfitting.
Random forests are a powerful method for non-parametric regression, but are limited in their ability to fit smooth signals, and can show poor predictive performance in the presence of strong, smooth effects. Taking the perspective of random forests as an adaptive kernel method, we pair the forest kernel with a local li…
Performing exact Bayesian inference for complex models is computationally intractable. Markov chain Monte Carlo (MCMC) algorithms can provide reliable approximations of the posterior distribution but are expensive for large datasets and high-dimensional models. A standard approach to mitigate this complexity consists i…
We study how the round-off (or discretization) error changes the statistical properties of a Gaussian long memory process. We show that the autocovariance and the spectral density of the discretized process are asymptotically rescaled by a factor smaller than one, and we compute exactly this scaling factor. Consequentl…
Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL objective and thus generally converges to a policy different from the optimal gree…
Proves EM algorithm guarantees for hierarchical imitation learning.
The celebrated Monte Carlo method estimates an expensive-to-compute quantity by random sampling. Bandit-based Monte Carlo optimization is a general technique for computing the minimum of many such expensive-to-compute quantities by adaptive random sampling. The technique converts an optimization problem into a statisti…
A nonparametric two-sample test using a parametric integral probability metric
The paper analyzes the sliding regret of stochastic bandit algorithms.
New deep learning method solves stochastic control problems.
Enhances U-statistics for semi-supervised datasets using unlabeled data.
HAMBO estimates policy performance by hallucinating worst-case trajectories, providing valid lower bounds.
Recent work by Jacot et al. (2018) has shown that training a neural network using gradient descent in parameter space is related to kernel gradient descent in function space with respect to the Neural Tangent Kernel (NTK). Lee et al. (2019) built on this result by establishing that the output of a neural network traine…
Novel SVM approach for extreme quantile regression with heavy tailed inputs.
MOPI optimizes flexible set-valued mappings to achieve superior shape adaptivity in conformal prediction.
Sequential screening and dynamic regret in multi-armed bandits with arriving arms
An optimal dynamic treatment regime (DTR) consists of a sequence of decision rules in maximizing long-term benefits, which is applicable for chronic diseases such as HIV infection or cancer. In this paper, we develop a novel angle-based approach to search the optimal DTR under a multicategory treatment framework for su…
SCOTCH learns system structure from irregular time series using neural SDEs.
Study on learning strategies in matching markets with uncertain preferences.
The paper develops a minimax optimal method for high-dimensional regression using auxiliary data.
Improved DNN estimator with scalable subsampling for efficient inference.
Paper explores properties of slice-matching operators for measure transfer.
Autonomous agents that must exhibit flexible and broad capabilities will need to be equipped with large repertoires of skills. Defining each skill with a manually-designed reward function limits this repertoire and imposes a manual engineering burden. Self-supervised agents that set their own goals can automate this pr…
We consider a problem of data integration. Consider determining which genes affect a disease. The genes, which we call predictor objects, can be measured in different experiments on the same individual. We address the question of finding which genes are predictors of disease by any of the experiments. Our formulation i…
In this paper, we study the problem of computing -statistics of degree , i.e., quantities that come in the form of averages over pairs of data points, in the local model of differential privacy (LDP). The class of -statistics covers many statistical estimates of interest, including Gini mean difference, Kendal…
Weight decay stabilizes training dynamics by slowing progressive sharpening.
Proposes a neural network method to combine nonprobability and probability survey samples.
WSFN overcomes saddle points for non-convex functionals in Wasserstein space.