arXiv research

Proposes a new model for high-dimensional data analysis with unknown link function.

ZSPO optimizes RL from unknown link functions using human feedback.

Study tackles nonlinear factor models with unknown monotone links from incomplete and noisy data.

Gradient flow solves multi-index regression for high-dimensional Gaussian data.

New method optimizes policies without assuming known link functions between preferences and rewards.

This work uses diffusion models for accurate signal recovery from semi-parametric models.

A new growth model for dynamic networks using Markovian latent points.

Existing nonconvex statistical optimization theory and methods crucially rely on the correct specification of the underlying "true" statistical models. To address this issue, we take a first step towards taming model misspecification by studying the high-dimensional sparse phase retrieval problem with misspecified link…

New algorithms for generalized linear bandits with unknown reward functions.

We present a max-margin nonparametric latent feature model, which unites the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction and automatically infer the unknown latent social dimension. By minimizing a hinge-loss using the linear expectation operat…

Efficiently learns Single-Index Models with constant factor approximation.

Linear regression studies the problem of estimating a model parameter $β^* \in \mathbb{R}^p$, from $n$ observations $\{(y_i,\mathbf{x}_i)\}_{i=1}^n$ from linear model $y_i = \langle \mathbf{x}_i,β^* \rangle + ε_i$. We consider a significant generalization in which the relationship between $\langle \mathbf{x}_i,β^* \ran…

The colored Jones polynomial is a $q$-polynomial invariant of links colored by irreducible representations of a simple Lie algebra. A $q$-series called a tail is obtained as the limit of the $\mathfrak{sl}_2$ colored Jones polynomials $\{J_n(K;q)\}_n$ for some link $K$, for example, an alternating link. For the $\mathf…

Solves inventory control with unknown demand trend using singular control.

We study the problem of recovering a structured signal $\mathbf{x}_0$ from high-dimensional data $\mathbf{y}_i=f(\mathbf{a}_i^T\mathbf{x}_0)$ for some nonlinear (and potentially unknown) link function $f$, when the regressors $\mathbf{a}_i$ are iid Gaussian. Brillinger (1982) showed that ordinary least-squares estimate…

Link prediction is a fundamental task in statistical network analysis. Recent advances have been made on learning flexible nonparametric Bayesian latent feature models for link prediction. In this paper, we present a max-margin learning method for such nonparametric latent feature relational models. Our approach attemp…

Paper detects checkerboard colorability of virtual links using odd writhe and arrow polynomial.

Random geometric graphs are a popular choice for a latent points generative model for networks. Their definition is based on a sample of $n$ points $X_1,X_2,\cdots,X_n$ on the Euclidean sphere~$\mathbb{S}^{d-1}$ which represents the latent positions of nodes of the network. The connection probabilities between the node…

A path integral on a link complement of a three-sphere fixes a vector (the "link state") in Chern-Simons theory. The link state can be written in a certain basis with the colored link invariants as its coefficients. We use symmetric webs to systematically compute the colored link invariants, by which we can write down …

Proposes a transfer learning framework for sparse SIMs without raw source data.

New neural networks learn single-index models efficiently.

In this paper, we propose an unifying view of several recently proposed structured sparsity-inducing norms. We consider the situation of a model simultaneously (a) penalized by a set- function de ned on the support of the unknown parameter vector which represents prior knowledge on supports, and (b) regularized in Lp-n…

Computing unlinking number is usually very difficult and complex problem, therefore we define BJ-unlinking number and recall Bernhard-Jablan conjecture stating that the classical unknotting/unlinking number is equal to the BJ-unlinking number. We compute BJ-unlinking number for various families of knots and links for w…

We consider ill-posed inverse problems where the forward operator $T$ is unknown, and instead we have access to training data consisting of functions $f_i$ and their noisy images $Tf_i$. This is a practically relevant and challenging problem which current methods are able to solve only under strong assumptions on the t…

FILTER model uses fusion penalized logistic threshold regression for high-dimensional data with unknown cut points.

Study vineyards linking TDA and knot theory, showing rich topological features.

Reconstructing weighted networks from partial information is necessary in many important circumstances, e.g. for a correct estimation of systemic risk. It has been shown that, in order to achieve an accurate reconstruction, it is crucial to reliably replicate the empirical degree sequence, which is however unknown in m…

New upper bound on Jones polynomial for fibered positive links.

New formulas for spatial 2-bouquet graphs discovered.

New obstructions show links with vanishing Milnor invariants may not be concordant to homology boundary links.

We introduce a matrix representation of a chord on a tangle which leads us to representing tangle chord diagrams as stacks of matrices that we call books. We show that band sum moves, Reidemeister moves as well as orientation changes are implemented on \widetilde{Z}_f - a framed link invariant constructed from the Kont…

The universal sl_2 invariant of string links has a universality property for the colored Jones polynomial of links, and takes values in the h-adic completed tensor powers of the quantized enveloping algebra of sl_2. In this paper, we exhibit explicit relationships between the universal sl_2 invariant and Milnor invaria…

The paper models and predicts co-occurrence counts using Gamma regression.

AI agent learns to handle unknown unknown states in reinforcement learning.

A new GP framework for discovering unknown functions and hypergraph structure.

Constructs non-asymptotic confidence regions for unknown functions in RKHS.

PGD algorithms solve nonlinear inverse problems with generative priors using noisy measurements.

Gradient descent can efficiently learn a target function with diverse and near-orthogonal features.

Dualities in physics help in machine learning tasks.

New algorithm POO optimizes noisy, unknown-smooth functions.

We show that the Artin representation on concordance classes of string links induces a well-defined epimorphism modulo order n twisted Whitney tower concordance, and that the kernel of this map is generated by band sums of iterated Bing-doubles of any string knot with nonzero Arf invariant. We also continue J. Levine's…

New method for fair resource allocation in AI-aware networks with unknown utility functions.

New method approximates M-estimator and predictions without solving fixed-point equations.

For links with vanishing pairwise linking numbers, the link components bound pairwise disjoint surfaces in $B^{4}$. In this paper, we describe the set of genera of such surfaces in terms of the $h$-function, which is a link invariant from Heegaard Floer homology. In particular, we use the $h$-function to give lower bou…

Paper calculates braid indices for reverse parallel links of alternating knots.

A new estimator for evaluating policies in unknown environments.

Kernelized bandit algorithm tackles adaptive contextual bandits with single-index models.

New link invariants from diagram colorings match link widths.