arXiv research

New data accumulation prevents model collapse in generative models.

Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue . They are based on the statistical analysis of accumulated and moving window data subsets with construction of a kurtosis-skewness diagram. This approach was applied to the data gat…

In many large-scale machine learning applications, data are accumulated with time, and thus, an appropriate model should be able to update in an online paradigm. Moreover, as the whole data volume is unknown when constructing the model, it is desired to scan each data item only once with a storage independent with the …

Improves likelihood-free inference by using a new sampling approach to avoid biased data collection.

Efforts to reduce the numerical precision of computations in deep learning training have yielded systems that aggressively quantize weights and activations, yet employ wide high-precision accumulators for partial sums in inner-product operations to preserve the quality of convergence. The absence of any framework to an…

Accumulated stock returns exhibit tempered skew t-distribution.

Unified framework models neural decision-making, improving accuracy.

Unfolding paths in Outer space accumulate on a simplex, not converge.

The aim of the present article is to offer a strictly mathematical, statistical treatment of the current account balances in EU and in the Eurozone. Based on Eurostat data, an overview of the total and annual balances is first made for different collections among the EU countries. Then, using the Mathematica technical …

Wealth inequality is an important matter for economic theory and policy. Ongoing debates have been discussing recent rise in wealth inequality in connection with recent development of active financial markets around the world. Existing literature on wealth distribution connects the origins of wealth inequality with a v…

Tutorial on using neural networks for single cell data analysis.

Machines, not humans, are the world's dominant knowledge accumulators but humans remain the dominant decision makers. Interpreting and disseminating the knowledge accumulated by machines requires expertise, time, and is prone to failure. The problem of how best to convey accumulated knowledge from computers to humans i…

Study robustness of global feature effect explanations in machine learning models.

Study of historic stock returns distributions, highlighting asymmetry and outliers.

Knowhow in societies accumulates as it gets transmitted from group to group, and from generation to generation. However, we lack of a unified quantitative formalism that takes into account the structured process for how this accumulation occurs, and this has precluded the development of a unified view of human developm…

In this paper, finite type domains with hyperbolic orbit accumulation points are studied. We prove, in case of $\mathbb{C}^2$, it has to be a (global) pseudoconvex domain, after an assumption of boundary regularity. Moreover, one of the applications will realize the classification of domains within this class, precisel…

Bias correction needed after deep learning regression training.

Paper tackles Byzantine resilience in distributed multi-task learning.

This paper presents a numerical model to solve the problem of cash accumulation strategies for products with an unknown future price, like assets. Stock prices are modeled by a discretized Wiener Process, and by the means of ordinary integrals this Wiener Process will be exactly matched at a preset terminal time. Three…

Analyzes multi-day stock returns, showing linear volatility and mean dependence.

Improved statistical computation through efficient matrix sampling.

Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning makes a batch processing of each task, implying that a data collection step is requi…

A multi-step framework tackles online unsupervised domain adaptation with novel mean-target subspace computation.

This paper presents a model of capital accumulation for a large number of heterogenous producer-consumers in an exchange space in which interactions depend on agents' positions. Each agent is described by his production, consumption, stock of capital, as well as the position he occupies in this abstract space. Each age…

WrapNet optimizes inference for low-resolution neural networks by using 8-bit additions.

Flexible model captures commodity skews with maturity effects.

This work addresses the instability in asynchronous data parallel optimization. It does so by introducing a novel distributed optimizer which is able to efficiently optimize a centralized model under communication constraints. The optimizer achieves this by pushing a normalized sequence of first-order gradients to a pa…

For any nonorientable closed surface, we determine the minimal dilatation among pseudo-Anosov mapping classes arising from Penner's construction. We deduce that the sequence of minimal Penner dilatations has exactly two accumulation points, in contrast to the case of orientable surfaces where there is only one accumula…

Improves matrix multiplication throughput for asymmetric bit-width operands.

The paper improves self-training in semi-supervised learning by selecting more robust pseudo-labeled data.

Paper excludes the lowest energy level as an accumulation point for harmonic maps into analytic manifolds.

We consider a family of manifolds with a class of degenerating warped product metrics $g_ε=ρ(ε,t)^{2a}dt^2 +ρ(ε,t)^{2b}ds_M^2$, with $M$ compact, $ρ$ homogeneous degree one, $a \le -1$ and $b > 0$. We study the Laplace operator acting on $L^{2}$ differential $p$-forms and give sharp accumulation rates for eigenvalues n…

Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and actor-critic methods are highly sensitive to the data distribution, and can make only …

In this paper we consider sparse approximation problems, that is, general $l_0$ minimization problems with the $l_0$-"norm" of a vector being a part of constraints or objective function. In particular, we first study the first-order optimality conditions for these problems. We then propose penalty decomposition (PD) me…

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many situations it is preferable to delay a decision rather than run the risk of making …

In this paper we continue our study of the Laplacian on manifolds with axial analytic asymptotically cylindrical ends initiated in~arXiv:1003.2538. By using the complex scaling method and the Phragmén-Lindelöf principle we prove exponential decay of the eigenfunctions corresponding to the non-threshold eigenvalues of t…

AdaX improves Adam by exponentially accumulating past gradients, leading to better performance in machine learning tasks.

FetchSGD reduces communication in federated learning with sketching.

Twin-to-twin transfusion syndrome treatment requires fetoscopic laser photocoagulation of placental vascular anastomoses to regulate blood flow to both fetuses. Limited field-of-view (FoV) and low visual quality during fetoscopy make it challenging to identify all vascular connections. Mosaicking can align multiple ove…

The paper analyzes how synthetic data training degrades diffusion models, providing bounds and characterizing different drift regimes.

Generative diffusion models improve financial LOB simulation and forecasting.

In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose empirical loss is under satisfactory statistical accuracy. Our proposed method is multistage in which the solution of a stage serves as a warm star…

New study shows MLE can avoid model collapse with gradual synthetic data addition.

The paper establishes criteria for spacetime inextendibility using asymptotic volume-distance-ratio analysis.

Study compares price limit and circuit breaker effects in stock markets.

We consider in this paper the regularity problem for time-optimal trajectories of a single-input control-affine system on a n-dimensional manifold. We prove that, under generic conditions on the drift and the controlled vector field, any control u associated with an optimal trajectory is smooth out of a countable set o…

Study of homeomorphisms on infinite type surfaces with a classification theorem.

The purpose of this study is to measure the Total Factor Productivity (TFP) growth and determine the share of each of the economic growth sources in the mining sector of Iran. The time period of this study is 1355-1385 of the Solar Hijri calendar (roughly overlaying with the time period of 1976-2006 of the Gregorian ca…