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.
Develops a new approach to establish universality for any-dimensional machine learning models.
Neural networks adapt to any input dimensionality.
New modular forms for anomaly cancellation formulas on any dimensional manifolds.
In this paper, we establish some general Kastler-Kalau-Walze type theorems for any dimensional manifolds with boundary which generalize the results in [WW1].
It is shown that the diffeomorphism type of the complement to a real space line arrangement in any dimensional affine ambient space is determined only by the number of lines and the data on multiple points.
New method uses scalars to approximate physics functions.
There are several types of equation of motion of elastic wires. In this paper, we treat an equation taking account of the thickness of wire. The equation was introduced by Caflisch and Maddocks on plane curves, and they proved the existence of solutions. Koiso and Sugimoto generalized the result to any dimensional Eucl…
Automatic sleep staging is a challenging problem and state-of-the-art algorithms have not yet reached satisfactory performance to be used instead of manual scoring by a sleep technician. Much research has been done to find good feature representations that extract the useful information to correctly classify each epoch…
We consider a quadratic form defined on the surfaces with parallel mean curvature vector of an any dimensional complex space form and prove that its -part is holomorphic. When the complex dimension of the ambient space is equal to we define a second quadratic form with the same property and then determine th…
We present a new method for the separation of superimposed, independent, auto-correlated components from noisy multi-channel measurement. The presented method simultaneously reconstructs and separates the components, taking all channels into account and thereby increases the effective signal-to-noise ratio considerably…
PPI++ uses machine learning predictions to improve inference from small datasets.
The main purpose of this paper is to prove a sharp Sobolev inequality in an exterior of a convex bounded domain. There are two ingredients in the proof: One is the observation of some new isoperimetric inequalities with partial free boundary, and the other is an integral inequality (due to Duff [9]) for any nonnegative…
In this paper we prove the infinitesimal uniqueness theorem for the Newton potential of non simply connected bodies using the singularity theory approach. We consider the Newtonian potentials of the domains in boundaries of which are the vanishing cycles on the level hypersurface of a holomorphic function w…
New compact mean convex hypersurfaces found for positive λ.
A new measure identifies clusters without assuming data distribution.
Most data is multi-dimensional. Discovering whether any subset of dimensions, or subspaces, of such data is significantly correlated is a core task in data mining. To do so, we require a measure that quantifies how correlated a subspace is. For practical use, such a measure should be universal in the sense that it capt…
One approach for constructing copula functions is by multiplication. Given that products of cumulative distribution functions (CDFs) are also CDFs, an adjustment to this multiplication will result in a copula model, as discussed by Liebscher (J Mult Analysis, 2008). Parameterizing models via products of CDFs has some a…
Financial institutions now face the important challenge of having to do multiple portfolio revaluations for their risk computation. The list is almost endless: from XVAs to FRTB, stress testing programs, etc. These computations require from several hundred up to a few million revaluations. The cost of implementing thes…
Adaptive framework improves nonparametric dimensionality reduction.
New method upscales models and transfers hyperparameters efficiently.
Machine learning approximates Calabi-Yau Hodge numbers from weight systems.
Sequencer algorithm detects main trends in complex datasets.
Diffusion-weighted magnetic resonance imaging (DWI) and fiber tractography are the only methods to measure the structure of the white matter in the living human brain. The diffusion signal has been modelled as the combined contribution from many individual fascicles of nerve fibers passing through each location in the …
ETC improves Transformer models for long and structured inputs.
Unified method for input, data, and model uncertainty in neural networks.
Improves sample efficiency in reinforcement learning with input representation.
Detects unusual inputs to neural networks to prevent flawed predictions.
TVS-FNNs can approximate any continuous function on expanded input spaces.
We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on…
A new method builds sparse polynomial chaos expansions for models with dependent inputs.
Centroid Transformers reduce memory and computation by summarizing inputs into centroids.
Methods for combining predictions from different models in a supervised learning setting must somehow estimate/predict the quality of a model's predictions at unknown future inputs. Many of these methods (often implicitly) make the assumption that the test inputs are identical to the training inputs, which is seldom re…
Testing under what conditions the product satisfies the desired properties is a fundamental problem in manufacturing industry. If the condition and the property are respectively regarded as the input and the output of a black-box function, this task can be interpreted as the problem called Level Set Estimation (LSE) --…
IA-BMA adapts model weights to inputs for better predictions.
Recent work establishes dataset difficulty and removes annotation artifacts via partial-input baselines (e.g., hypothesis-only models for SNLI or question-only models for VQA). When a partial-input baseline gets high accuracy, a dataset is cheatable. However, the converse is not necessarily true: the failure of a parti…
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., -perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse …
Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adver…
AIRBO optimizes robustly under uncertain inputs.
When simulating a complex stochastic system, the behavior of output response depends on input parameters estimated from finite real-world data, and the finiteness of data brings input uncertainty into the system. The quantification of the impact of input uncertainty on output response has been extensively studied. Most…
We present a novel framework for specifying and verifying correctness globally for neural networks on perception tasks. Most previous works on neural network verification for perception tasks focus on robustness verification. Unlike robustness verification, which aims to verify that the prediction of a network is stabl…
Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.
This paper aims to propose a novel deep learning-integrated framework for deriving reliable simulation input models through incorporating multi-source information. The framework sources and extracts multisource data generated from construction operations, which provides rich information for input modeling. The framewor…
SpinSVAR estimates SVAR models with sparse input, improving accuracy and scalability.
New method distinguishes predictive distribution estimators in high-dimensional inputs.
This research analyzes how input and output layers affect deep neural networks' resistance to adversarial attacks.
Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created by humans are often treated as a given. We investigate how inputs of humans can…
New method certifies neural network robustness under random input noise.
In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein s…