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.
Optimized biopharmaceutical seed train design reduces variability and saves time.
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 …
Study on how intraclass variability affects Temporal Ensembling accuracy.
Regularization improves stability and consistency of sparse autoencoders.
User-generated reviews can be decomposed into fine-grained segments (e.g., sentences, clauses), each evaluating a different aspect of the principal entity (e.g., price, quality, appearance). Automatically detecting these aspects can be useful for both users and downstream opinion mining applications. Current supervised…
The paper proposes a method to stabilize predictions by identifying causal variables using a seed variable.
Paper tackles graph matching with partially correct seeds, improving performance guarantees.
The paper shows how shared random seeds can reduce variance in machine learning evaluations.
New method stabilizes machine learning predictions across random seeds.
Fairness audits fail under missing protected labels, especially at zero access.
Study finds many Lagrangian fillings for certain Legendrian links.
MONSTOR estimates influence in unseen networks with high accuracy.
A new method averages neural network parameters to rank features robustly.
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…
We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possible to train on millions of frames per second but also to lower the cost of experiments compared to current methods. We achieve this with a …
Non-determinism from GPUs dominates ResNet training accuracy variability.
Study finds optimal learning rate schedules for sub-100M quantization-aware training across bit-widths.
We present a weakly-supervised data augmentation approach to improve Named Entity Recognition (NER) in a challenging domain: extracting biomedical entities (e.g., proteins) from the scientific literature. First, we train a neural NER (NNER) model over a small seed of fully-labeled examples. Second, we use a reference s…
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…
New method finds 198,846 toric-colorable seeds of Picard number 5.
PNN-smoothing improves -means clustering by merging subsets' clusterings.
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…
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…
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…
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…
Bayesian optimization outperforms other methods in hyperparameter tuning for reinforcement learning.
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.
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data. Additional unlabelled speech data is employed through a data selection mechanism …
New method measures model variability from stochastic optimization.
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…
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.
TOO optimizes stochastic epidemiological models by finding both parameter settings and random seeds.
OmniMatch algorithm perfectly matches graphs without edge correlation.
Study compares nine deep learning architectures for multi-horizon financial forecasting.
A cluster variety of Fock and Goncharov is a scheme constructed from the data related to the cluster algebras of Fomin and Zelevinsky. A seed is a combinatorial data which can be encoded as an matrix with integer entries, or as a quiver in special cases, together with formal variables. A mutation is a c…
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…
Quantum annealing (QA) is a hardware-based heuristic optimization and sampling method applicable to discrete undirected graphical models. While similar to simulated annealing, QA relies on quantum, rather than thermal, effects to explore complex search spaces. For many classes of problems, QA is known to offer computat…
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…
We provide initial seedings to the Quick Shift clustering algorithm, which approximate the locally high-density regions of the data. Such seedings act as more stable and expressive cluster-cores than the singleton modes found by Quick Shift. We establish statistical consistency guarantees for this modification. We then…
The paper proves there are many Lagrangian fillings for Legendrian links of affine type.