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.
CrossBeam learns to search more efficiently in program synthesis.
BUSTLE synthesizes programs by learning from intermediate values.
Subspace clustering aims to find groups of similar objects (clusters) that exist in lower dimensional subspaces from a high dimensional dataset. It has a wide range of applications, such as analysing high dimensional sensor data or DNA sequences. However, existing algorithms have limitations in finding clusters in non-…
Paper introduces TEP to better model treatment effect heterogeneity.
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.
TF-Coder simplifies tensor manipulation programming in TensorFlow.
BOinG optimizes HPO problems by focusing on promising local regions.
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…
Bayesian tensor factorization approximates a complex tree model.
Extends PCVM for multi-class classification with improved accuracy.
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…
New method restores source features for SFDA without source data.
System designs for analyzing and pricing non-performing consumer credit portfolios.
Study improves forecasting of aggregated curves in electricity markets.
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…
Distribution feeder long-term load forecast (LTLF) is a critical task many electric utility companies perform on an annual basis. The goal of this task is to forecast the annual load of distribution feeders. The previous top-down and bottom-up LTLF methods are unable to incorporate different levels of information. This…
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…
This paper compares Grid Search, Random Search, and Genetic Algorithm for NAS.
NFM improves deep learning by selectively processing hidden states.
A clustering algorithm for natural hierarchical clusters with near-linear time complexity.
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…
The paper introduces a method to make neural networks more robust to adversarial attacks.
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…
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.
A new language for neural architecture search decouples search spaces and algorithms.
Many proteoforms - arising from alternative splicing, post-translational modifications (PTMs), or paralogous genes - have distinct biological functions, such as histone PTM proteoforms. However, their quantification by existing bottom-up mass-spectrometry (MS) methods is undermined by peptide-specific biases. To avoid …
New protocol benchmarks deep learning methods' data efficiency.
NAS helps find best neural network designs.
One endeavour of modern physical chemistry is to use bottom-up approaches to design materials and drugs with desired properties. Here we introduce an atomistic structure learning algorithm (ASLA) that utilizes a convolutional neural network to build 2D compounds and layered structures atom by atom. The algorithm takes …
Petridish efficiently searches neural architectures by iteratively adding shortcut connections.
New hierarchical search algorithm improves neural architecture design across different operator sets.
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…
A new algorithm, Regular Tree Search, tackles non-convex simulation optimization problems.
Approaches to learning Bayesian networks from data typically combine a scoring function with a heuristic search procedure. Given a Bayesian network structure, many of the scoring functions derived in the literature return a score for the entire equivalence class to which the structure belongs. When using such a scoring…
Modern machine learning algorithms are increasingly computationally demanding, requiring specialized hardware and distributed computation to achieve high performance in a reasonable time frame. Many hyperparameter search algorithms have been proposed for improving the efficiency of model selection, however their adapta…
Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.
New algorithms improve contextual search in the presence of adversarial corruptions.
NATS-Bench benchmarks NAS algorithms for architecture topology and size.
Casting machine learning as a type of search, we demonstrate that the proportion of problems that are favorable for a fixed algorithm is strictly bounded, such that no single algorithm can perform well over a large fraction of them. Our results explain why we must either continue to develop new learning methods year af…
FLOP algorithm speeds up causal structure learning for linear models.
In the field of Natural Language Processing (NLP), we revisit the well-known word embedding algorithm word2vec. Word embeddings identify words by vectors such that the words' distributional similarity is captured. Unexpectedly, besides semantic similarity even relational similarity has been shown to be captured in word…
Quality-Diversity algorithms explore multiple high-performing solutions in a search space.
We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neurocognitively-grounded approach in the context of unsupervised generative modeling of sequences. Specifically, we build on the concept of predi…
Empirical comparison of 18 hyperparameter tuning algorithms for SVM.