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.
Bottom-up algorithms outperform top-down in hierarchical community detection at intermediate levels.
Attention mechanism combines bottom-up and top-down signals in neural networks.
BUSTLE synthesizes programs by learning from intermediate values.
Efficient unsupervised training and inference in deep generative models remains a challenging problem. One basic approach, called Helmholtz machine, involves training a top-down directed generative model together with a bottom-up auxiliary model used for approximate inference. Recent results indicate that better genera…
CrossBeam learns to search more efficiently in program synthesis.
Scalable subspace clustering for high-dimensional data.
New method restores source features for SFDA without source data.
Novel non-parametric tree model learns tree distributions.
System designs for analyzing and pricing non-performing consumer credit portfolios.
Study improves forecasting of aggregated curves in electricity markets.
We study analytically and numerically Minsky instability as a combination of top-down, bottom-up and peer-to-peer positive feedback loops. The peer-to-peer interactions are represented by the links of a network formed by the connections between firms, contagion leading to avalanches and percolation phase transitions pr…
Hybrid method forecasts distribution feeder loads using LSTM and GRU networks.
Bayesian tensor factorization approximates a complex tree model.
Panoptic-DeepLab achieves state-of-the-art results in panoptic segmentation.
We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gat…
We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and predict…
Multilayer bootstrap network builds a gradually narrowed multilayer nonlinear network from bottom up for unsupervised nonlinear dimensionality reduction. Each layer of the network is a nonparametric density estimator. It consists of a group of k-centroids clusterings. Each clustering randomly selects data points with r…
Study explores robust Orlicz spaces in finance, showing separability implications.
We introduce a new Bayesian model for hierarchical clustering based on a prior over trees called Kingman's coalescent. We develop novel greedy and sequential Monte Carlo inferences which operate in a bottom-up agglomerative fashion. We show experimentally the superiority of our algorithms over others, and demonstrate o…
A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of th…
We show that a generative random field model, which we call generative ConvNet, can be derived from the commonly used discriminative ConvNet, by assuming a ConvNet for multi-category classification and assuming one of the categories is a base category generated by a reference distribution. If we further assume that the…
In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network. Our model consists of a top-down stack of GANs, each learned to generate lower-level representations conditioned on …
A new multi-phase approach improves supply chain forecasting accuracy.
Efficiently learns linear non-Gaussian DAGs with noisy nodes.
Extends PCVM for multi-class classification with improved accuracy.
NFM improves deep learning by selectively processing hidden states.
BOinG optimizes HPO problems by focusing on promising local regions.
Paper introduces TEP to better model treatment effect heterogeneity.
Paper uses 2-step Gradient Boosting to predict VAT tax gap.
We describe a bottom-up framework, based on the identification of appropriate order parameters and determination of phase diagrams, for understanding progressively refined agent-based models and simulations of financial markets. We illustrate this framework by starting with a deterministic toy model, whereby indepe…
The paper introduces a method to make neural networks more robust to adversarial attacks.
A generative Bayesian model is developed for deep (multi-layer) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up and top-down probabilistic learning. After learning the deep convolutional dictionary, testing is implemented via dec…
This paper describes a flexible and tractable bottom-up dynamic correlation modelling framework with a consistent stochastic recovery specification. The stochastic recovery specification only models the first two moments of the spot recovery rate as its higher moments have almost no contribution to the loss distributio…
Agent-based model uses SAM to create realistic economic system.
LIBRE learns interpretable Boolean rules from data.
Finiteness predicts dualities in quantum gravity.
Deep neural networks blend mechanistic and phenomenological NLP approaches.
Model learns collective and individual dynamics in time series data.
We propose a new technique, Singular Vector Canonical Correlation Analysis (SVCCA), a tool for quickly comparing two representations in a way that is both invariant to affine transform (allowing comparison between different layers and networks) and fast to compute (allowing more comparisons to be calculated than with p…
This paper is trying to unveil general statistical characteristic of financial; time series data that is subjected to several financial time series data present in Indonesia, e.g. individual index such as stock price of PT. TELKOM, stock price of PT HM SAMPOERNA, and compiled stock price index (Jakarta Stock Exchange I…
Developed HIquant to quantify proteoforms accurately without biases.
TF-GNN simplifies graph neural networks in TensorFlow.
A clustering algorithm for natural hierarchical clusters with near-linear time complexity.
We consider a set of probabilistic functions of some input variables as a representation of the inputs. We present bounds on how informative a representation is about input data. We extend these bounds to hierarchical representations so that we can quantify the contribution of each layer towards capturing the informati…
New techniques reuse subword embeddings in neural models, reducing size and improving performance.
We propose to prune a random forest (RF) for resource-constrained prediction. We first construct a RF and then prune it to optimize expected feature cost & accuracy. We pose pruning RFs as a novel 0-1 integer program with linear constraints that encourages feature re-use. We establish total unimodularity of the constra…
Novel ML approach optimizes large portfolios without covariance matrix issues.
The traditional sparse modeling approach, when applied to inverse problems with large data such as images, essentially assumes a sparse model for small overlapping data patches. While producing state-of-the-art results, this methodology is suboptimal, as it does not attempt to model the entire global signal in any mean…