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.
Study on optimal rates for sequential probability assignment using smoothed analysis.
New bounds on minimax regret for sequential probability assignment using logarithmic loss.
Framework for sorting with diverse value models and valued assignment examples.
New study shows low-degree polynomial algorithms struggle at clause densities close to Fix's.
A new method uses optimal transport for semi-supervised classification.
The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data. A leading design paradigm for this is the convolution kernel, which decomposes structured objects into their parts and sums over all pairs of parts. Assignment kernels, in contrast, are ob…
We consider the problem of learning a measure of distance among vectors in a feature space and propose a hybrid method that simultaneously learns from similarity ratings assigned to pairs of vectors and class labels assigned to individual vectors. Our method is based on a generative model in which class labels can prov…
A new method for few-shot learning using Laplacian regularization.
Review and compare sorting model selection methods for preference disaggregation.
Study minimax regret in sequential probability assignment with and without side information.
Generative model for joint discrete distributions using randomized assignment flows.
Deep learning improves cancer report classification accuracy.
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 …
Study compares methods for treatment assignment, finding A-learner best for playlist generation.
We show that all versions of Heegaard Floer homology, link Floer homology, and sutured Floer homology are natural. That is, they assign concrete groups to each based 3-manifold, based link, and balanced sutured manifold, respectively. Furthermore, we functorially assign isomorphisms to (based) diffeomorphisms, and show…
Quantum theory uses modular group representations to assign invariants to 3-manifolds.
In this note we introduce a construction which assigns to an arbitrary manifold bundle its fiberwise orientation covering. This is used to show that the zeta classes of unoriented surface bundles are not divisible in the stable range.
SCRIB assigns multiple labels to each example to control class-specific prediction risks.
New method for sequential probability assignment reduces regret using contextual Shtarkov sums.
Kronheimer and Mrowka defined invariants of balanced sutured manifolds using monopole and instanton Floer homology. Their invariants assign isomorphism classes of modules to balanced sutured manifolds. In this paper, we introduce refinements of these invariants which assign much richer algebraic objects called projecti…
Loss assigns examples to classes and superclasses in hierarchical data.
Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss function used in this context is the cross-entropy loss, which reduces to the log loss in the typical case when there is a single correct r…
Untrained neural networks can unfairly assign predictions to the same class.
Extends Fisher's Discriminant Analysis for interval-valued data.
Unified view on selective credit assignment for reinforcement learning.
The article proves a lower semicontinuity property of holonomy maps.
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…
Classification may not be reliable for several reasons: noise in the data, insufficient input information, overlapping distributions and sharp definition of classes. Faced with several possibilities neural network may in such cases still be useful if instead of a classification elimination of improbable classes is done…
In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to each observation which is then modified by applying the domain specific transforma…
New method certifies deep graph classifiers with tighter risk bounds.
This paper compares unstructured and structured EM-based semi-supervised learning methods.
BFPM improves machine learning accuracy by considering object types and memberships flexibly.
New algorithms assign credit to past decisions based on hindsight.
Improves domain adaptation by clustering target representations.
Study projective flat vector bundles over Riemann surfaces using Wronskian line bundles.
We show that if is a class A Lorentzian 2-torus with timelike poles, then there exists a Lipschitz foliation by complete future-directed timelike geodesics with any pre-assigned asymptotic direction in the interior of the stable time cone. This is done by constructing certain solutions to…
Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to …
We present a novel active learning algorithm for community detection on networks. Our proposed algorithm uses a Maximal Expected Model Change (MEMC) criterion for querying network nodes label assignments. MEMC detects nodes that maximally change the community assignment likelihood model following a query. Our method is…
EgalMAB solves fair resource allocation in stochastic bandits.
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…
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…
COCOA improves credit assignment in reinforcement learning by measuring contributions to rewards.
Domain generalization is the problem of assigning labels to an unlabeled data set, given several similar data sets for which labels have been provided. Despite considerable interest in this problem over the last decade, there has been no theoretical analysis in the setting of multi-class classification. In this work, w…
The p-Laplacian Transformer improves transformer models by assigning higher attention weights to tokens in close proximity.
In this short note, we compare the combinatorial sign assignment of Manolescu, Ozsvath, Szabo and Thurston for grid homology of knots and links in 3-sphere with the sign assignment coming from a coherent system of orientations on Whitney disks. Although these constructions produce different signs, a small modification …
Prototype-based memory network learns visual categories from unlabeled data.
New methods optimize personalized treatment assignment in trials with many arms.
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 …