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.
New method stabilizes machine learning predictions across random seeds.
The paper shows how shared random seeds can reduce variance in machine learning evaluations.
Bayesian optimization is a powerful tool for expensive stochastic black-box optimization problems such as simulation-based optimization or machine learning hyperparameter tuning. Many stochastic objective functions implicitly require a random number seed as input. By explicitly reusing a seed a user can exploit common …
In this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness of the model in general. We specifically perform a controlled study on the effect of random seeds on the behaviour of attention, gradient-bas…
TOO optimizes stochastic epidemiological models by finding both parameter settings and random seeds.
Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called "reproducibility crisis" in deep reinforcement learning. In this tutorial paper, we explain how the number of random seeds relates to the probabilities of statistical errors. …
We describe the first known mean-field study of landing probabilities for random walks on hypergraphs. In particular, we examine clique-expansion and tensor methods and evaluate their mean-field characteristics over a class of random hypergraph models for the purpose of seed-set community expansion. We describe paramet…
Fairness audits fail under missing protected labels, especially at zero access.
OmniMatch algorithm perfectly matches graphs without edge correlation.
This article contains the first published example of a real economic balance sheet where the Solvency II ratio substantially depends on the seed selected for the random number generator (RNG) used. The theoretical background and the main quality criteria for RNGs are explained in detail. To serve as a gauge for RNGs, a…
Bayesian optimization outperforms other methods in hyperparameter tuning for reinforcement learning.
Regularization improves stability and consistency of sparse autoencoders.
We present a parallelized bijective graph matching algorithm that leverages seeds and is designed to match very large graphs. Our algorithm combines spectral graph embedding with existing state-of-the-art seeded graph matching procedures. We justify our approach by proving that modestly correlated, large stochastic blo…
PNN-smoothing improves -means clustering by merging subsets' clusterings.
Community detection is, at its core, an attempt to attach an interpretable function to an otherwise indecipherable form. The importance of labeling communities has obvious implications for identifying clusters in social networks, but it has a number of equally relevant applications in product recommendations, biologica…
New Karger-like algorithms solve graph cuts, useful for image segmentation.
A new method averages neural network parameters to rank features robustly.
We study a well known noisy model of the graph isomorphism problem. In this model, the goal is to perfectly recover the vertex correspondence between two edge-correlated Erdős-Rényi random graphs, with an initial seed set of correctly matched vertex pairs revealed as side information. For seeded problems, our result pr…
Introducing noise in the training of machine learning systems is a powerful way to protect individual privacy via differential privacy guarantees, but comes at a cost to utility. This work looks at whether the inherent randomness of stochastic gradient descent (SGD) could contribute to privacy, effectively reducing the…
A new protocol evaluates small machine learning improvements conservatively.
We show that the stochasticity in training ResNets for image classification on GPUs in TensorFlow is dominated by the non-determinism from GPUs, rather than by the initialisation of the weights and biases of the network or by the sequence of minibatches given. The standard deviation of test set accuracy is 0.02 with fi…
We present FIESTA, a model selection approach that significantly reduces the computational resources required to reliably identify state-of-the-art performance from large collections of candidate models. Despite being known to produce unreliable comparisons, it is still common practice to compare model evaluations base…
Paper tackles graph matching with partially correct seeds, improving performance guarantees.
In the k-nearest neighbor algorithm (k-NN), the determination of classes for test instances is usually performed via a majority vote system, which may ignore the similarities among data. In this research, the researcher proposes an approach to fine-tune the selection of neighbors to be passed to the majority vote syste…
We reproduced the results of CheXNet with fixed hyperparameters and 50 different random seeds to identify 14 finding in chest radiographs (x-rays). Because CheXNet fine-tunes a pre-trained DenseNet, the random seed affects the ordering of the batches of training data but not the initialized model weights. We found subs…
Study finds many Lagrangian fillings for certain Legendrian links.
New method fills cluster seeds with exact Lagrangian structures.
Many methods for automated software test generation, including some that explicitly use machine learning (and some that use ML more broadly conceived) derive new tests from existing tests (often referred to as seeds). Often, the seed tests from which new tests are derived are manually constructed, or at least simpler t…
In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^-4) differences for state-of-the-art systems. For …
New method finds 198,846 toric-colorable seeds of Picard number 5.
Optimized biopharmaceutical seed train design reduces variability and saves time.
Study on how intraclass variability affects Temporal Ensembling accuracy.
Given two graphs, the graph matching problem is to align the two vertex sets so as to minimize the number of adjacency disagreements between the two graphs. The seeded graph matching problem is the graph matching problem when we are first given a partial alignment that we are tasked with completing. In this paper, we m…
Data-aware methods for dimensionality reduction and matrix decomposition aim to find low-dimensional structure in a collection of data. Classical approaches discover such structure by learning a basis that can efficiently express the collection. Recently, "self expression", the idea of using a small subset of data vect…
Interpreting neural network decisions and the information learned in intermediate layers is still a challenge due to the opaque internal state and shared non-linear interactions. Although (Kim et al, 2017) proposed to interpret intermediate layers by quantifying its ability to distinguish a user-defined concept (from r…
Study compares nine deep learning architectures for multi-horizon financial forecasting.
We present a novel approximate graph matching algorithm that incorporates seeded data into the graph matching paradigm. Our Joint Optimization of Fidelity and Commensurability (JOFC) algorithm embeds two graphs into a common Euclidean space where the matching inference task can be performed. Through real and simulated …
Efficiently selects seed nodes to maximize content influence in unknown social networks.
Eradicating hunger and malnutrition is a key development goal of the 21st century. We address the problem of optimally identifying seed varieties to reliably increase crop yield within a risk-sensitive decision-making framework. Specifically, we introduce a novel hierarchical machine learning mechanism for predicting c…
We prove that for a generic -dimensional integrable rolling distribution of contact elements (excluding developable seed and isotropic developable leaves) isometric correspondence of leaves of a general nature (independent of the shape of the seed) requires the Bäcklund transformation.
Paper proves uniqueness of a complex construction.
PPM improves graph matching for correlated Gaussian Wigner models with high probability.
Derivative-informed models improve financial surrogates for accurate hedging and risk management.
Study finds significant instability in node embeddings due to randomness.
New method measures model variability from stochastic optimization.
Discrete knot theory models use lattice-filtered graphs to detect merging knot components.
New method uses cluster shapes to improve track finding in particle collisions.
A novel validation method improves feature importance analysis in subject-specific ML models.