Research
On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

149298447596 · Jun 202019922001200920172026
48 results for Universal Weight Systems

New weight systems derived from a specific Lie algebra for knot invariants.

problem Constructing universal weight systems for knot invariants.
method Using a minimal Z22\mathbb{Z}_2^2-graded Lie algebra to create weight systems.
result Weight system derived from A1εA1_ε shows hybrid properties of sl(2)sl(2) and gl(11)gl(1|1).

Echo state networks with random weights can approximate any continuous system.

problem Approximating continuous dynamical systems using echo state networks.
method Randomly generated internal weights and a sampling procedure for activation functions.
result Echo state networks with random weights can approximate any continuous casual time-invariant operators with high probability.

We give a construction of Kirby weight systems associated to sl(2) and valued into the finite field Z/pZ. We show that it is possible to apply this sequence of weight systems on the universal invariant of framed link. We also show that the corresponding sequence admits a Fermat limit, which defines an asymptotic ration…

1998-02-15abs ↗pdf ↗

Neural networks with learned biases can approximate any function.

problem Whether neural networks with only learned biases can approximate any continuous function.
method Theoretical and numerical analysis of random weights and learned biases in neural networks.
result Feedforward and recurrent neural networks with random weights can approximate any continuous function and dynamical systems.

DeepRSCN models nonlinear systems using stochastic configurations.

problem Modeling nonlinear dynamic systems efficiently.
method Incrementally constructed deep reservoir computing framework with random parameters and online weight updates.
result DeepRSCN outperforms single-layer networks in efficiency, learning, and generalization.

The paper calculates a specific weight system for chord diagrams with a particular graph structure.

problem Calculating a specific weight system for chord diagrams with a complete bipartite graph structure.
method Using a Lie algebra sl3\mathfrak{sl}_3 and its weight system, the authors derive a function on chord diagrams.
result The authors compute the sl3\mathfrak{sl}_3 weight system for chord diagrams with a complete bipartite graph structure.

Pulling back the weight system associated with the exceptional Lie algebra G_2 by a modification of the universal Vassiliev-Kontsevich invariant yields a link invariant; extending it to 3-nets, we derive a recursive algorithm for its evaluation.

1998-06-24abs ↗pdf ↗

The universal sl_2 invariant of string links has a universality property for the colored Jones polynomial of links, and takes values in the h-adic completed tensor powers of the quantized enveloping algebra of sl_2. In this paper, we exhibit explicit relationships between the universal sl_2 invariant and Milnor invaria…

2014-05-13abs ↗pdf ↗

MAT combines meta-learning and adversarial training to defend against universal patches.

problem Defending against universal patches that fool models in various contexts.
method Meta adversarial training (MAT) integrates meta-learning with adversarial training.
result MAT increases robustness against universal patch attacks on image classification and traffic-light detection.

Ideas of Rozansky and Witten, as developed by Kapranov, show that a complex symplectic manifold X gives rise to Vassiliev weight systems. In this paper we study these weight systems by using D(X), the derived category of coherent sheaves on X. The main idea (stated here a little imprecisely) is that D(X) is the categor…

2006-02-28abs ↗pdf ↗

We prove the existence of a degree 7 Vassiliev invariant of long (or string) two-component links which is not preserved under the simultaneous change of orientation of both components. The non-invertibility of this invariant can be detected by the standard weight system with values in the tensor square of the universal…

2005-07-01abs ↗pdf ↗

The paper shows neural networks can approximate functions over non-compact domains with non-polynomial activation.

problem Approximating functions over non-compact domains using neural networks.
method Using single-hidden-layer feedforward neural networks with non-polynomial activation functions over non-compact subsets of Euclidean spaces.
result Neural networks can approximate functions in weighted CkC^k-spaces and weighted Sobolev spaces over unbounded domains.

Deep residual networks can approximate any continuous function using control theory.

problem Universal approximation capabilities of deep residual neural networks.
method Relating residual networks to control systems and using Lie algebraic techniques.
result Deep residual networks with adequately deep layers can approximate any continuous function on a compact set.

Functional input neural networks approximate continuous functions on weighted spaces.

problem Approximating continuous functions on infinite-dimensional weighted spaces.
method Additive family mapping, non-linear activation, linear readouts, Stone-Weierstrass theorem.
result Global universal approximation of continuous functions on weighted spaces.

This work shows MLPs can approximate monotonic functions without bounded activations.

problem Optimizing MLPs with monotonic constraints and bounded activations.
method Generalized theoretical results showing MLPs with non-negative weights and saturating activations are universal approximators.
result MLPs with non-negative weights and saturating activations are universal approximators for monotonic functions.

Kernel methods have been widely applied to machine learning and other questions of approximating an unknown function from its finite sample data. To ensure arbitrary accuracy of such approximation, various denseness conditions are imposed on the selected kernel. This note contributes to the study of universal, characte…

2013-10-21abs ↗pdf ↗

ESNs trained with Tikhonov least squares approximate ergodic dynamical systems in L2(μ) norm.

problem Approximating ergodic dynamical systems using ESNs.
method Tikhonov least squares regression on ESNs trained on observations from an ergodic dynamical system.
result ESNs trained with Tikhonov least squares approximate the target function in the L2(μ) norm.

Generalizes neural network approximation to infinite-dimensional manifolds and derivatives.

problem Approximating differentiable maps on infinite-dimensional manifolds.
method Proves a weighted Nachbin theorem to establish universal approximation for differentiable maps, including derivatives.
result Linear functions of the signature can approximate path space functionals including their derivatives.

Rozansky and Witten proposed a 3-dimensional sigma-model whose target space is a hyperkähler manifold. They conjectured that this theory has an associated TQFT, with Hilbert spaces given by certain cohomology groups of the hyperkähler manifold. On the other hand, there is a certain modified TQFT constructed by Murakami…

2000-09-25abs ↗pdf ↗

Random matrix analysis reveals that neural network weights are mostly random, with some indicating learned information.

problem Understanding how neural networks store information needed for tasks.
method Random matrix theory (RMT) applied to weight matrices of trained deep neural networks.
result Most singular values and eigenvectors of trained neural networks follow universal RMT predictions, suggesting they are random and do not contain system-specific information.

Enhances RSCNs with hybrid regularization for nonlinear dynamics.

problem Modeling nonlinear dynamic systems with uncertainties.
method Recurrent stochastic configuration networks with hybrid regularization.
result The method outperforms other models in nonlinear system identification and industrial tasks.

Two new methods generate probabilistic forecasts of individual treatment effects.

problem Generating probabilistic forecasts of individual treatment effects for risk-aware decision-making.
method Proposes CCT and CMC meta-learners combining conformal predictive systems with analytic convolution or Monte Carlo sampling.
result Achieve probabilistically calibrated predictive distributions and performant continuous ranked probability scores.

To a rational homology sphere graph manifold one can associate a weighted tree invariant called splice diagram. It was shown earlier that the splice diagram determines the universal abelian cover of the manifold. We will in this article turn the proof of this in to an algorithm to explicitly construct the universal abe…

2010-11-02abs ↗pdf ↗

Universal approximation for ODENet and ResNet with a single activation function.

problem Approximating complex dynamical systems with limited vector fields.
method Examined ODENet and ResNet with vector fields composed of a single activation function and affine mapping.
result ODENet and ResNet with restricted vector fields can uniformly approximate those with general vector fields.

Survey on computational models in dynamical systems, including new universality concepts.

problem Understanding the relationship between computational models and dynamical systems.
method Review of recent works on Turing universality, Topological Kleene Field Theories, and dynamical bordisms.
result Introduction of new perspectives on computability through dynamical systems.

Consider a family of portfolio strategies with the aim of achieving the asymptotic growth rate of the best one. The idea behind Cover's universal portfolio is to build a wealth-weighted average which can be viewed as a buy-and-hold portfolio of portfolios. When an optimal portfolio exists, the wealth-weighted average c…

2015-10-09abs ↗pdf ↗

In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likel…

2019-05-09abs ↗pdf ↗

Universal approximation for stochastic processes using Brownian motion.

problem Approximating stochastic processes with linear functionals.
method Establishing LpL^p-type universal approximation theorems for rough path spaces.
result Linear functionals on the signature of time-extended Brownian motion can approximate any pp-integrable stochastic process.

The paper shows instability in Minkowski spacetime for a quantum system.

problem Linear instability of the semiclassical Einstein-Klein-Gordon system in Minkowski spacetime.
method Formulated a forcing problem for metric and state perturbations, used tensor decomposition and quantum Møller operator.
result Metric perturbations grow exponentially, bounded by a universal scale H, indicating quantum backreaction.

MarketSenseAI system outperforms passive benchmarks by 25.2% on S&P 500, adding value over random selection.

problem Identifying alpha in stock recommendations from multi-agent LLM systems.
method Deployed multi-agent LLM equity system generating live signals, combining four specialist agents into a synthesis agent.
result Strong-buy equal-weight portfolio on S&P 500 earns +2.18%/month, significantly outperforming passive benchmarks.

Bandlimited random neural networks may not approximate all functions perfectly.

problem Expressive power of shallow neural networks with bandlimited random weights.
method Ridgelet analysis for deriving approximation error lower bounds.
result Bandlimited random weights can lead to non-zero approximation error.