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.
GP-DRF model handles variable-sized input and learns deep features.
Paper introduces new bounds linking data compressibility to generalization error.
New hypergraph neural network learns variable-sized hyperedges.
In this paper, we investigate the significance of choosing an appropriate tessellation strategy for a spatio-temporal taxi demand-supply modeling framework. Our study compares (i) the variable-sized polygon based Voronoi tessellation, and (ii) the fixed-sized grid based Geohash tessellation, using taxi demand-supply GP…
Two Bayesian optimization methods tackle dynamic design spaces with mixed variables.
Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to rep…
We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because th…
Bin Packing problems have been widely studied because of their broad applications in different domains. Known as a set of NP-hard problems, they have different vari- ations and many heuristics have been proposed for obtaining approximate solutions. Specifically, for the 1D variable sized bin packing problem, the two ke…
Improved taxi demand-supply forecasts using graph-based LSTM.
Study compares RL and SL for TSP, finds RL better for variable graph sizes.
Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner. Providing a concatenation of features in an arbitrary order may lead to the learning of spurious patterns or biases that do not actually exist. Another complication is introduced …
Persistent homology (PH) is a rigorous mathematical theory that provides a robust descriptor of data in the form of persistence diagrams (PDs) which are 2D multisets of points. Their variable size makes them, however, difficult to combine with typical machine learning workflows. In this paper we introduce persistence c…
Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal. Previous methods for this task require manual feature engineering, huge memory requirements and large execution times. To the best of our …
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE c…
Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain qu…
New method makes machine learning approximations unbiased and efficient.
AdaptiveNet tackles disease progression prediction in rheumatoid arthritis using deep neural networks.
We consider a simple and overarching representation for permutation-invariant functions of sequences (or multiset functions). Our approach, which we call Janossy pooling, expresses a permutation-invariant function as the average of a permutation-sensitive function applied to all reorderings of the input sequence. This …
A new distance for mixed-variable, hierarchical datasets with meta variables.
FREDE efficiently embeds graphs using linear space and guarantees quality.
Learning representation for graph classification turns a variable-size graph into a fixed-size vector (or matrix). Such a representation works nicely with algebraic manipulations. Here we introduce a simple method to augment an attributed graph with a virtual node that is bidirectionally connected to all existing nodes…
We consider large scale empirical risk minimization (ERM) problems, where both the problem dimension and variable size is large. In these cases, most second order methods are infeasible due to the high cost in both computing the Hessian over all samples and computing its inverse in high dimensions. In this paper, we pr…
New method estimates graphons from multiple networks with high accuracy and low complexity.
Reinforcement Patching optimizes dynamic sequence patching for efficient time series forecasting.
Proposes a new optimization-based method for aggregating sets in neural networks.
The relationship between the size and the variance of firm growth rates is known to follow an approximate power-law behavior where is the firm size and is an exponent weakly dependent on . Here we show how a model of proportional growth which treats firms as classes compos…
Graph Laplacian spectrum serves as a robust feature representation.
Hyper-SAGNN learns patterns in hypergraphs for complex interactions.
We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically so…
Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the sequence-to-sequence (seq2seq) framework which employs the chain rule to efficiently repre…
A new differentiable divergence for time series comparison.
We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size substructures which are related to the labels in some ways. We believe that uncovering these relations might hold the key to classification performance and explainability. We intro…
Deep Sets improve reinforcement learning for autonomous driving with variable inputs.
Online distributional prediction with latent cluster geometry
Methods for learning feature representations for Offline Handwritten Signature Verification have been successfully proposed in recent literature, using Deep Convolutional Neural Networks to learn representations from signature pixels. Such methods reported large performance improvements compared to handcrafted feature …
RS-Del provides robustness for sequence classifiers against edit distance attacks.
Deep RL learns to construct objects from 2D images by avoiding brick overlaps.
The market events of 2007-2009 have reinvigorated the search for realistic return models that capture greater likelihoods of extreme movements. In this paper we model the medium-term log-return dynamics in a market with both fundamental and technical traders. This is based on a Poisson trade arrival model with variable…
Data preprocessing improves data quality for robust data mining.
Big data sets must be carefully partitioned into statistically similar data subsets that can be used as representative samples for big data analysis tasks. In this paper, we propose the random sample partition (RSP) data model to represent a big data set as a set of non-overlapping data subsets, called RSP data blocks,…
A new method for handling imbalanced big data using ensembles and smart data.
Prevents sensitive data generation in diffusion models using labeled and unlabeled data.
Study reveals Data Shapley's inconsistent performance in data selection tasks.
PRRO generates synthetic tabular data that improves SL performance and class distribution.
Defines data science as a natural ecosystem with challenges and missions.
Synthetic data enhances analytics but requires careful volume management.
This paper introduces C-DSL to improve data mining outcomes by considering context.
Proposes using probabilistic models for privacy-preserving synthetic data.