arXiv research

Framework for sorting with diverse value models and valued assignment examples.

We present new results concerning the solvability, of lack thereof, in the Cauchy problem for the debar operator, with initial values assigned on a weakly pseudoconvex hypersurface, and provide illustrative examples.

We consider the problem of learning soft assignments of $N$ items to $K$ categories given two sources of information: an item-category similarity matrix, which encourages items to be assigned to categories they are similar to (and to not be assigned to categories they are dissimilar to), and an item-item similarity mat…

Unified view on selective credit assignment for reinforcement learning.

The paper formalizes and analyzes multi-agent Q-learning with value factorization.

New algorithms assign credit to past decisions based on hindsight.

A new framework assigns values to data points considering their distribution.

Review and compare sorting model selection methods for preference disaggregation.

Many problems in machine learning can be expressed by means of a graph with nodes representing training samples and edges representing the relationship between samples in terms of similarity, temporal proximity, or label information. Graphs can in turn be represented by matrices. A special example is the Laplacian matr…

Eigenoptions improve credit assignment in reinforcement learning.

Error bounds based on worst likely assignments use permutation tests to validate classifiers. Worst likely assignments can produce effective bounds even for data sets with 100 or fewer training examples. This paper introduces a statistic for use in the permutation tests of worst likely assignments that improves error b…

Mixture models and topic models generate each observation from a single cluster, but standard variational posteriors for each observation assign positive probability to all possible clusters. This requires dense storage and runtime costs that scale with the total number of clusters, even though typically only a few clu…

We analyze the problem of sequential probability assignment for binary outcomes with side information and logarithmic loss, where regret---or, redundancy---is measured with respect to a (possibly infinite) class of experts. We provide upper and lower bounds for minimax regret in terms of sequential complexities of the …

The paper describes new types of picture-valued invariants and their applications.

A new PLL method uses class activation values to improve robustness.

Given a connected real Lie group and a contractible homogeneous proper $G$--space $X$ furnished with a $G$--invariant volume form, a real valued volume can be assigned to any representation $ρ\colon π_1(M)\to G$ for any oriented closed smooth manifold $M$ of the same dimension as $X$. Suppose that $G$ contains a closed…

How do we assign value to economic transactions? To answer this question, we must consider whether the value of objects is inherent, is a product of social interaction, or involves other mechanisms. Economic theory predicts that there is an optimal price for any market transaction, and can be observed during auctions o…

Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit to training set biases and label noises. In addition to various regularizers, example reweighting algorithms are popular solutions to these p…

New pseudo-Hermitian models from non-semisimple TQFTs.

The p-Laplacian Transformer improves transformer models by assigning higher attention weights to tokens in close proximity.

New framework for modular reinforcement learning reduces sample complexity.

Assignment methods are at the heart of many algorithms for unsupervised learning and clustering - in particular, the well-known K-means and Expectation-Maximization (EM) algorithms. In this work, we study several different methods of assignment, including the "hard" assignments used by K-means and the ?soft' assignment…

A new method uses optimal transport for semi-supervised classification.

Shapley Flow interprets model predictions using a graph-based approach to feature importance.

Various applications involve assigning discrete label values to a collection of objects based on some pairwise noisy data. Due to the discrete---and hence nonconvex---structure of the problem, computing the optimal assignment (e.g.~maximum likelihood assignment) becomes intractable at first sight. This paper makes prog…

Study compares methods for treatment assignment, finding A-learner best for playlist generation.

Extends Fisher's Discriminant Analysis for interval-valued data.

Algorithm solves job acceptance problem with random arrivals and values.

Machine learning and C-NLP improve emergency department triage accuracy.

We give a combinatorial model for r-spin surfaces with parametrised boundary based on Novak (2015). The r-spin structure is encoded in terms of $\mathbb{Z}_r$-valued indices assigned to the edges of a polygonal decomposition. This combinatorial model is designed for our state sum construction of two-dimensional topolog…

moment maps arise as a generalization of genuine moment maps on symplectic manifolds when the symplectic structure is discarded, but the relation between the mapping and the action is kept. Particular examples of abstract moment maps had been used in Hamiltonian mechanics for some time, but the abstract notion originat…

Metaheuristics optimize portfolios with pre-assignment and margin trading for better risk-adjusted returns.

In many machine learning applications, we are faced with incomplete datasets. In the literature, missing data imputation techniques have been mostly concerned with filling missing values. However, the existence of missing values is synonymous with uncertainties not only over the distribution of missing values but also …

New causal versions of MaxEnt and PIR avoid paradoxical probability updates.

A model explains credit assignment in deep learning networks.

Set risk measures extend traditional risk measures to handle sets of positions.

LICA learns credit assignment for cooperative agents without explicit formulation.

New deep learning framework for tabular data clusters with interpretable features.

Optimal treatment regimes (OTR) are individualised treatment assignment strategies that identify a medical treatment as optimal given all background information available on the individual. We discuss Bayes optimal treatment regimes estimated using a loss function defined on the bivariate distribution of dichotomous po…

Given discrete time observations over a fixed time interval, we study a nonparametric Bayesian approach to estimation of the volatility coefficient of a stochastic differential equation. We postulate a histogram-type prior on the volatility with piecewise constant realisations on bins forming a partition of the time in…

A celebrated theorem of Hadwiger states that the Euler-Poincaré characteristic is the the unique invariant and continuous valuation on the distributive lattice of compact polyhedra in R^n that assigns value one to each convex non-empty such polyhedron. This paper provides an analogue of Hadwiger's result for finitely p…

The $k$th-nearest neighbor rule is arguably the simplest and most intuitively appealing nonparametric classification procedure. However, application of this method is inhibited by lack of knowledge about its properties, in particular, about the manner in which it is influenced by the value of $k$; and by the absence of…

Bayesian method estimates contamination factor for unsupervised anomaly detection.

Researchers develop a method to infer reference measures from observed functionals.

Machine learning models are vulnerable to adversarial examples. An adversary modifies the input data such that humans still assign the same label, however, machine learning models misclassify it. Previous approaches in the literature demonstrated that adversarial examples can even be generated for the remotely hosted m…

New mathematical proposal for TQFTs using TMF-modules.

Introduces group-valued momentum maps for symplectic fiber bundles.

GOAT improves graph matching speed and accuracy using optimal transport.