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.
Rarely switch policies to optimize treatment effects, reducing harmful changes.
ACE improves counterfactual explanations with fewer model queries.
Detecting the emergence of abrupt property changes in time series is a challenging problem. Kernel two-sample test has been studied for this task which makes fewer assumptions on the distributions than traditional parametric approaches. However, selecting kernels is non-trivial in practice. Although kernel selection fo…
This work benchmarks neural embeddings for link prediction in evolving knowledge graphs.
It is important to identify the change point of a system's health status, which usually signifies an incipient fault under development. The One-Class Support Vector Machine (OC-SVM) is a popular machine learning model for anomaly detection and hence could be used for identifying change points; however, it is sometimes …
Study assesses CNN model robustness to noise in low-cost CT scans.
Detecting the emergence of an abrupt change-point is a classic problem in statistics and machine learning. Kernel-based nonparametric statistics have been used for this task which enjoy fewer assumptions on the distributions than the parametric approach and can handle high-dimensional data. In this paper we focus on th…
The splitting number of a link is the minimal number of crossing changes between different components required, on any diagram, to convert it to a split link. We introduce new techniques to compute the splitting number, involving covering links and Alexander invariants. As an application, we completely determine the sp…
The paper establishes conditions for link invariants to bound the weak splitting number.
The unknotting number of a knot is the minimum number of crossings one must change to turn that knot into the unknot. The algebraic unknotting number is the minimum number of crossing changes needed to transform a knot into an Alexander polynomial-one knot. We work with a generalization of unknotting number due to Math…
Changing kernel bandwidth during training improves kernel regression performance.
This paper investigates how machine learning APIs change over time and proposes an efficient method to monitor these changes.
We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time efficiency. In the proposed method, we introduce a sparsity-inducing prior on the per u…
Two algorithms improve performance in piecewise-stationary cascading bandits.
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change …
SIG model identifies invariant variables for MSDA with fewer domain constraints.
Equivariant CNNs improve RL performance in symmetric environments.
New algorithm tracks subspaces with missing and corrupted data, simpler and federated.
The Turaev genus and dealternating number of a link are two invariants that measure how far away a link is from alternating. We determine the Turaev genus of a torus knot with five or fewer strands either exactly or up to an error of at most one. We also determine the dealternating number of a torus knot with five or f…
Efficiently processes dynamic inputs in AI writing assistants with incremental computation.
Probabilistic representations of movement primitives open important new possibilities for machine learning in robotics. These representations are able to capture the variability of the demonstrations from a teacher as a probability distribution over trajectories, providing a sensible region of exploration and the abili…
Stabilizes GAN training with limited data.
Method trains sparse neural networks without sacrificing accuracy.
Jones polynomial coincidences explored for rational knots.
New diagonal move simplifies knots and links efficiently.
Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer more parallelism and hence better computational efficiency. We have developed a n…
The concordance orders of many algebraic order two knots of ten or fewer crossings have been heretofore unknown. We use Casson-Gordon invariants and twisted Alexander polynomials to find that, in all but one case, these knots do not have concordance order two. We also find that a certain family of algebraic order two t…
Classifiers deployed in the real world operate in a dynamic environment, where the data distribution can change over time. These changes, referred to as concept drift, can cause the predictive performance of the classifier to drop over time, thereby making it obsolete. To be of any real use, these classifiers need to d…
AdaQuantFL reduces communication in federated learning by adaptively quantizing model updates.
We investigate the bi-orderability of two-bridge knot groups and the groups of knots with 12 or fewer crossings by applying recent theorems of Chiswell, Glass and Wilson. Amongst all knots with 12 or fewer crossings (of which there are 2977), previous theorems were only able to determine bi-orderability of 599 of the c…
This paper shows feature importance remains valid even in low-performing models.
We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we leverage this approximate model along with a notion of reachability using Mean First P…
S2cGAN uses fewer labels to train cGANs effectively.
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well …
Hyperbolic knots are not common among prime knots.
Tiny benchmarks reduce LLM evaluation costs by using fewer examples.
Scientists and engineers rely on accurate mathematical models to quantify the objects of their studies, which are often high-dimensional. Unfortunately, high-dimensional models are inherently difficult, i.e. when observations are sparse or expensive to determine. One way to address this problem is to approximate the or…
GGAN improves audio representation learning with fewer labels.
The paper uses a novel framework to learn option prices by imitating principal investor behavior.
Study shows hyperbolic links are not common among prime links.
ActiveLab improves classifier accuracy with fewer annotations by re-labeling.
BOBYQA optimizes deep networks with fewer queries than other methods.
Improved accuracy with fewer labels using MixMatch and active learning.
Improved spectral clustering with fewer eigenvectors performs better.
Deep CNNs struggle with rare taxa; one-class classifiers help identify them.
This work uses action equivariance to learn structured latent spaces for reinforcement learning.
Efficient exploration improves large language model performance with fewer queries.
In this paper, we compute the slice genus for many low-crossing virtual knots. For instance, we show that 1295 out of 92800 virtual knots with 6 or fewer crossings are slice, and that all but 248 of the rest are not slice. Key to these results are computations of Turaev's graded genus, which we show extends to give an …