arXiv research

New method computes first Vassiliev derivative of Khovanov homology.

Convolutional sparse coding (CSC) can learn representative shift-invariant patterns from multiple kinds of data. However, existing CSC methods can only model noises from Gaussian distribution, which is restrictive and unrealistic. In this paper, we propose a general CSC model capable of dealing with complicated unknown…

Low-rank representation~(LRR) has been a significant method for segmenting data that are generated from a union of subspaces. It is, however, known that solving the LRR program is challenging in terms of time complexity and memory footprint, in that the size of the nuclear norm regularized matrix is $n$-by-$n$ (where $…

We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis. In contrast to other state-of-the-art approaches, the toolkit we develop is rather minimal: it uses a single, off-the-shelf classifier for all these tasks. The crux of our approach is that …

K. Ding studied a class of Schubert varieties X_λin type A partial flag manifolds, corresponding to integer partitions λand in bijection with dominant permutations. He observed that the Schubert cell structure of X_λis indexed by maximal rook placements on the Ferrers board B_λ, and that the integral cohomology groups …

Solved a conjecture about rational homology projective planes with quotient singularities.

Proposes a method to measure similarity between anomaly scores from different methods.

Let $G = N \rtimes A$, where $N$ is a stratified group and $A = \mathbb{R}$ acts on $N$ via automorphic dilations. Homogeneous sub-Laplacians on $N$ and $A$ can be lifted to left-invariant operators on $G$ and their sum is a sub-Laplacian $Δ$ on $G$. Here we prove weak type $(1,1)$, $L^p$-boundedness for $p \in (1,2]$ …

Trust lies at the crux of most economic transactions, with credit markets being a notable example. Drawing on insights from the literature on coordination games and network growth, we develop a simple model to clarify how trust breaks down in financial systems. We show how the arrival of bad news about a financial agen…

Algorithm ensures fair ranking by minority groups alongside majority groups.

Improved decision tree learning guarantees for complex functions.

The problem of attempting to learn the mapping between data and labels is the crux of any machine learning task. It is, therefore, of interest to the machine learning community on practical as well as theoretical counts to consider the existence of a test or criterion for deciding the feasibility of attempting to learn…

Scoring functions (SFs), which measure the plausibility of triplets in knowledge graph (KG), have become the crux of KG embedding. Lots of SFs, which target at capturing different kinds of relations in KGs, have been designed by humans in recent years. However, as relations can exhibit complex patterns that are hard to…

Transformers learn algorithms for in-context learning with bounds and stability analysis.

A fundamental task in kernel methods is to pick nodes and weights, so as to approximate a given function from an RKHS by the weighted sum of kernel translates located at the nodes. This is the crux of kernel density estimation, kernel quadrature, or interpolation from discrete samples. Furthermore, RKHSs offer a conven…

Convex clustering is a recent stable alternative to hierarchical clustering. It formulates the recovery of progressively coalescing clusters as a regularized convex problem. While convex clustering was originally designed for handling Euclidean distances between data points, in a growing number of applications, the dat…

Optimizes CM for stochastic convex optimization with progressive precision.

The paper solves integrable systems of PDEs, including famous equations.

The paper models and analyzes faults in TPU-based neural networks.

This is a sequel to the paper [Oh5] (or ArXiv:math.SG/0206092). The main purpose of the paper is to give the proof of an existence theorem, with energy bounds, of certain pseudo-holomorphic sections of the mapping cylinder that is needed for the proof of nondegeneracy of the homological invariant pseudo-norm which the …

P-SE explains model decisions with minimal feature subsets and fast estimators.

In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions. In this paper, we focus on improving the robustness of a large class of learning algorithms that are formulated as low-rank semi-definite programming (SDP) problems. Traditional formulations us…

This paper connects Wasserstein distances to MMD norms for compressive statistical learning.

A new method improves text generation quality and diversity.

Learning powerful data embeddings has become a center piece in machine learning, especially in natural language processing and computer vision domains. The crux of these embeddings is that they are pretrained on huge corpus of data in a unsupervised fashion, sometimes aided with transfer learning. However currently in …

A novel approach to federated learning with strong privacy guarantees.

This paper proposes a novel selective autoencoder approach within the framework of deep convolutional networks. The crux of the idea is to train a deep convolutional autoencoder to suppress undesired parts of an image frame while allowing the desired parts resulting in efficient object detection. The efficacy of the fr…

Method generates i.i.d. samples from GT data using space-time mixing.

Algorithm matches vertices of correlated Erdős-Rényi graphs efficiently.

Improved MMWU algorithm achieves instance-optimal regret bound for matrix LEA.

New findings show that common optimization algorithms struggle with random problems.

Proposes a method to integrate learner models robustly against misspecifications.

Meta-learning improves by adding more data to tasks.

Exploiting low-rank structure of the user-item rating matrix has been the crux of many recommendation engines. However, existing recommendation engines force raters with heterogeneous behavior profiles to map their intrinsic rating scales to a common rating scale (e.g. 1-5). This non-linear transformation of the rating…

New method for neural networks to predict histogram data.

In various application areas, networked data is collected by measuring interactions involving some specific set of core nodes. This results in a network dataset containing the core nodes along with a potentially much larger set of fringe nodes that all have at least one interaction with a core node. In many settings, t…

Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user. However, the stationary CB model may be too simple to apply to real-world problems, where user preferences may ch…

Deep linear networks oscillate beyond the edge of stability in a predictable manner.

Mixture modelling involves explaining some observed evidence using a combination of probability distributions. The crux of the problem is the inference of an optimal number of mixture components and their corresponding parameters. This paper discusses unsupervised learning of mixture models using the Bayesian Minimum M…

New methods learn sampling distributions for particle filters without supervision.

MV-GNN improves molecular property prediction by integrating atom and bond information.

Deep neural networks can achieve remarkable generalization performances while interpolating the training data perfectly. Rather than the U-curve emblematic of the bias-variance trade-off, their test error often follows a "double descent" - a mark of the beneficial role of overparametrization. In this work, we develop a…

Understanding the representational power of Deep Neural Networks (DNNs) and how their structural properties (e.g., depth, width, type of activation unit) affect the functions they can compute, has been an important yet challenging question in deep learning and approximation theory. In a seminal paper, Telgarsky highlig…

Numerous learning methods for fuzzy cognitive maps (FCMs), such as the Hebbian-based and the population-based learning methods, have been developed for modeling and simulating dynamic systems. However, these methods are faced with several obvious limitations. Most of these models are extremely time consuming when learn…

A new memory system handles non-stationary environments by self-sizing and retaining memories.

Gradient descent with small initialization solves matrix completion without regularization.

Algorithm minimizes control regret for non-stationary LQR systems.

New research shows no-regret learning is impossible in Markov games under certain assumptions.