arXiv research

GLR-klUCB detects change-points in non-stationary bandits efficiently.

Using Quillen's superconnection formalism we give a new "twisted" approach to the rational Gromov-Lawson-Rosenberg (GLR) conjecture on topological obstructions to the existence of Riemannian metrics of positive scalar curvature on compact spin manifolds. In particular, we present a short proof of the rational GLR conje…

Paper proposes a robust deep graph-based classifier for noisy labels.

New algorithm detects changes in combinatorial semi-bandit rewards.

We study sequential change-point detection procedures based on linear sketches of high-dimensional signal vectors using generalized likelihood ratio (GLR) statistics. The GLR statistics allow for an unknown post-change mean that represents an anomaly or novelty. We consider both fixed and time-varying projections, deri…

Unified stopping rules ensure accurate policies in contextual learning.

We consider the change-point detection problem of deciding, based on noisy measurements, whether an unknown signal over a given graph is constant or is instead piecewise constant over two connected induced subgraphs of relatively low cut size. We analyze the corresponding generalized likelihood ratio (GLR) statistics a…

The Gromov-Lawson-Rosenberg-conjecture for a group G states that a closed spin manifold M^n (n>4) with fundamental group G admits a metric with positive scalar curvature if and only if its C^*-index A(M) in KO_n(C^*_r(G)) vanishes. We prove this for groups G with low-dimensional classifying space, provided the assembly…

Improved online changepoint detection for autocorrelated data.

Characterizes symmetric Bernoulli distributions with minimal convex sums.

Upper bound on expected supremum of Bernoulli process.

Simple algorithm approximates rare event frequencies.

In this paper, we consider the multivariate Bernoulli distribution as a model to estimate the structure of graphs with binary nodes. This distribution is discussed in the framework of the exponential family, and its statistical properties regarding independence of the nodes are demonstrated. Importantly the model can e…

Finite index solutions to Bernoulli problem are always axially symmetric.

Proves a principle for one-phase Bernoulli problem minimizers.

A new distribution fixes a common error in VAEs, improving image quality.

Bayesian autoencoders improve OOD detection by addressing Bernoulli likelihood issues.

This paper proposed a new regression model called $l_1$-regularized outlier isolation and regression (LOIRE) and a fast algorithm based on block coordinate descent to solve this model. Besides, assuming outliers are gross errors following a Bernoulli process, this paper also presented a Bernoulli estimate model which, …

We solve Euler equations on graph manifolds, classifying steady flows with Morse-Bott Bernoulli functions.

The paper cleans label noise in supervised classification using Bernoulli sampling.

This paper tackles open problem of tight bounds for KBs with Bernoulli rewards.

Dasgupta and Shulman showed that a two-round variant of the EM algorithm can learn mixture of Gaussian distributions with near optimal precision with high probability if the Gaussian distributions are well separated and if the dimension is sufficiently high. In this paper, we generalize their theory to learning mixture…

Spectral method speeds fitting of binary time series models.

A new method for efficient nonlinear process monitoring using random Bernoulli features.

We study the fundamental problem of learning an unknown, smooth probability function via pointwise Bernoulli tests. We provide a scalable algorithm for efficiently solving this problem with rigorous guarantees. In particular, we prove the convergence rate of our posterior update rule to the true probability function in…

New method improves neural network robustness with brain-like learning.

A new method uses Mean Field Games to optimize mixture models of Bernoulli and categorical distributions.

A new algorithm resamples Bernoulli race particle filters using true weights.

First order invariants of generic immersions of manifolds of dimension nm-1 into manifolds of dimension n(m+1)-1, m,n>1 are constructed using the geometry of self-intersections. The range of one of these invariants is related to Bernoulli numbers. As by-products some geometrically defined invariants of regular homotopy…

New $L$-functions for 3-manifolds connect to Witten invariants and relate to generalized Bernoulli polynomials.

Improved regret bounds for DP-KLUCB and DP-IMED in Bernoulli bandits.

Paper compares credit portfolio risks using robust Bernoulli mixture models.

New acquisition functions improve Bernoulli LSE.

A new framework predicts links in time-dependent networks using Bernoulli autoregression.

Let $\{T^t\}$ be a smooth flow with positive speed and positive topological entropy on a compact smooth three dimensional manifold, and let $μ$ be an ergodic measure of maximal entropy. We show that either $\{T^t\}$ is Bernoulli, or $\{T^t\}$ is isomorphic to the product of a Bernoulli flow and a rotational flow. Appli…

The paper proves ML estimators are strongly consistent for identifying edge weights in BAR models.

BeMF improves recommendation reliability in recommender systems.

Feature selection problems have been extensively studied for linear estimation, for instance, Lasso, but less emphasis has been placed on feature selection for non-linear functions. In this study, we propose a method for feature selection in high-dimensional non-linear function estimation problems. The new procedure is…

Study analyzes symmetric two-armed Bernoulli bandit problem with zero mean gap.

Exact simulation of correlated binary outcomes using PMF constraints and linear programming.

A new sampling method balances multi-label datasets by preserving category frequency order.

A new RBM model handles both linear and log-amplitude spectrograms.

We introduce a novel multivariate random process producing Bernoulli outputs per dimension, that can possibly formalize binary interactions in various graphical structures and can be used to model opinion dynamics, epidemics, financial and biological time series data, etc. We call this a Bernoulli Autoregressive Proces…

Proposes a non-parametric method for deep discrete latent variable models.

The beta-Bernoulli process provides a Bayesian nonparametric prior for models involving collections of binary-valued features. A draw from the beta process yields an infinite collection of probabilities in the unit interval, and a draw from the Bernoulli process turns these into binary-valued features. Recent work has …

Improved training of GRBMs for image generation.

Estimates parameters of high-dimensional Bernoulli autoregressive process with long-range dependence.

Stability inequalities for specific solutions in high dimensions.