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.

168,657 papers · 148 categories

Trend · papers per month

166333499665 · Jun 202019922001200920172026
48 results for Collapsed Effective Operators

Introduce Collapsed Effective Operators for higher-order structures.

problem Existing spectral operators decompose topology into separate ranks, leaving practitioners to fuse information back to vertices.
method Introduce Collapsed Effective Operators via Schur complementation of a graded Laplacian.
result Preserves positive semi-definiteness, lowers system energy under higher-order connectivity.

Enhances neural architecture search efficiency and prevents performance collapse.

problem Improving memory efficiency and preventing performance collapse in neural architecture search.
method Employing continuous relaxation strategy and gradient-based optimization for over-parameterized BCNN construction, introducing Confident Learning Rate and partial channel connections.
result NAS-v2 delivers state-of-the-art search efficiency on CIFAR-10 and ImageNet.

This paper explains a mechanism called phase collapse that improves image classification accuracy.

problem Understanding the role of non-linearities and convolutional filters in image classification.
method Demonstrates phase collapse as a mechanism that eliminates spatial variability and linearly separates classes.
result Phase collapse improves classification accuracy, while thresholding operators degrade performance.

We compute the spectrum of the Dirac operator on 3-dimensional Heisenberg manifolds. The behavior under collapse to the 2-torus is studied. Depending on the spin structure either all eigenvalues tend to ±\pm\infty or there are eigenvalues converging to those of the torus. This is shown to be true in general for collap…

1998-01-20abs ↗pdf ↗

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networ…

2018-09-16abs ↗pdf ↗

We show characterizations of non-collapsed compact RCD(K,N)RCD(K, N) spaces, which in particular confirm a conjecture of De Philippis-Gigli on the implication from the weakly non-collapsed condition to the non-collapsed one in the compact case. The key idea is to give the explicit formula of the Laplacian associated to the p…

2019-04-30abs ↗pdf ↗

Paper shows stability of metric reconstruction for orbifolds from spectral data.

problem Determining the metric structure of collapsing orbifolds from spectral data.
method Improved quantitative unique continuation for wave operator on Riemannian manifolds.
result Quantitative stability of inverse problem for Riemannian orbifolds.

Similarity algebra extends algebraic structures with quantitative bounds.

problem Exact algebraic structures with strict axioms.
method Framework for approximate algebraic and Lie structures with ε\varepsilon-estimates.
result Similarity structures converge to classical algebraic objects as εightarrow0\varepsilon ightarrow 0.

ContraNorm prevents dimensional collapse in GNNs and Transformers.

problem Dimensional collapse in Graph Neural Networks and Transformers.
method Proposes ContraNorm, a novel normalization layer inspired by contrastive learning.
result Proves ContraNorm alleviates both complete and dimensional collapse under certain conditions.

We analyze the limit of the spectrum of a geometric Dirac-type operator under a collapse with bounded diameter and bounded sectional curvature. In the case of a smooth limit space B, we show that the limit of the spectrum is given by the spectrum of a certain first-order differential operator on B, which can be constru…

2000-05-01abs ↗pdf ↗

The paper establishes principles for initializing and designing GNNs with ReLU activations to avoid oversmoothing and correlation collapse.

problem Oversmoothing and correlation collapse in deep ReLU GNNs.
method The paper derives and validates three principles for initialization and architecture selection in finite width graph neural networks with ReLU activations.
result Correct initialization, residual aggregation operators, and residual connections significantly improve early training dynamics in deep ReLU GNNs.

The goal of the present paper is to calculate the limit spectrum of the Hodge-de Rham operator under the perturbation of collapsing one part of a manifold obtained by gluing together two manifolds with the same boundary. It appears to take place in the general problem of blowing up conical singularities as introduced i…

2010-07-17abs ↗pdf ↗

The paper explains how continuous language models can produce discrete, interpretable meanings.

problem Semantic collapse in continuous systems of large language models.
method Formalizing large language models as Continuous State Machines (CSMs) and analyzing the associated transfer operator.
result The leading eigenfunctions of the transfer operator induce a finite number of invariant meaning basins, explaining how continuous computation can produce discrete, interpretable semantics.

VINNAS uses variational inference to avoid mode collapse in neural architecture search.

problem Mode collapse in gradient-based NAS methods, leading to suboptimal architectures.
method Differentiable variational inference with variational dropout and automatic relevance determination.
result State-of-the-art accuracy with up to twice fewer non-zero parameters.

Study on removing sets and uniqueness of diffusion operators on various spaces.

problem Determining the effect of removing small sets on the self-adjointness and uniqueness of diffusion operators.
method Analyzes symmetric diffusion operators on metric measure spaces, proving a truncation result for potentials.
result Characterizes the critical size of removed sets and their effect on operator properties.

Study shows annealing with adaptive schedule reduces mode collapse in NFs for parameter estimation.

problem Mode collapse in normalizing flows for multimodal distributions.
method Annealing with an adaptive schedule based on effective sample size (ESS).
result Our approach reduces mode collapse and converges marginal likelihood faster than MCMC methods.

Deep Gaussian Processes with polynomial kernels can collapse rapidly without proper hyperparameter tuning.

problem The collapse of Deep Gaussian Processes with polynomial kernels without careful hyperparameter tuning.
method Analysis using the Berry-Esseen Theorem and observation of prior behavior.
result The prior of a Deep Gaussian Process collapses rapidly towards zero or places negligible mass on low norm functions without proper hyperparameter tuning.

Deep nets exhibit 'Neural Collapse' during training's final phase, simplifying decision-making.

problem Understanding and optimizing deep learning training phases.
method Direct measurements on three deepnet architectures across seven datasets.
result Deep nets exhibit 'Neural Collapse' during training's final phase, simplifying decision-making.

The paper proves extremal black holes form at a critical point of gravitational collapse.

problem Formation of extremal black holes in gravitational collapse.
method Constructing smooth families of spherically symmetric solutions to the Einstein-Maxwell-Vlasov system.
result Extremal Reissner-Nordström black holes form at the critical collapse threshold.

NPO method improves LLM unlearning without catastrophic collapse.

problem Efficiently unlearning undesirable data from LLMs without losing model utility.
method Negative Preference Optimization (NPO) method based on alignment.
result NPO-based methods achieve better unlearning results and maintain model utility.

Derives operational-time variance kernel for reaction boundaries in financial markets.

problem Separating components in volatility models to better understand market dynamics.
method Derives a variance kernel for a latent-order-book reaction boundary, separating structural boundary cumulant, clock projection, and pricing-measure choice.
result Operational variance has a closed asymptotic form for long-memory forcing, with effective signed-forcing intensity and resilience.

Derives variance kernel for reaction boundary in financial models.

problem Separating components in financial volatility models.
method Operational-time variance kernel, damped Abel response kernel, closed asymptotic form.
result Operational variance has a closed asymptotic form involving various parameters.

The paper studies gravitational instantons with flat limits and finds elliptic regularity estimates.

problem Analyzing gravitational instantons with flat limits using elliptic analysis.
method Establishing elliptic regularity estimates and showing uniform constants for a family of metrics.
result The Laplacian is Fredholm and an isomorphism between specific weighted spaces.

Verification helps prevent model collapse when training on synthesized data.

problem Model collapse when training on generated data.
method Theoretical characterization using Gaussian mixtures, linear classifiers, and linear verifiers to assess synthesized data quality.
result Verifiers can prevent model collapse and correlate with performance.

In narrow asymptotic settings Gaussian VAE models of continuous data have been shown to possess global optima aligned with ground-truth distributions. Even so, it is well known that poor solutions whereby the latent posterior collapses to an uninformative prior are sometimes obtained in practice. However, contrary to c…

2019-12-23abs ↗pdf ↗

This work tackles posterior collapse in conditional and hierarchical VAEs.

problem Posterior collapse in VAEs leads to poor latent variable representations.
method Theoretical analysis of linear conditional and hierarchical VAEs, empirical validation.
result Theoretical and empirical evidence of posterior collapse causes in conditional and hierarchical VAEs.

New analysis shows how attention masks and LayerNorm prevent rank collapse in transformers.

problem Rank collapse in transformer models with increasing depth.
method General analysis of rank collapse under self-attention, considering attention masks and LayerNorm.
result Self-attention with LayerNorm can prevent rank collapse and maintain a rich set of equilibria.

This work shows dimension regularization can replace skip-gram negative sampling for graph embeddings, improving efficiency and performance.

problem Efficiently enforcing dissimilarity among node embeddings in graph learning.
method Dimension regularization as an alternative to skip-gram negative sampling.
result Dimension regularization is a more efficient approach to enforcing dissimilarity in graph embeddings.

Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training. We study the issue of mode collapse of Boundary Equilibrium Generative Adversarial Network (BEGAN), which is one of the state-of-the-art generative models. Despite its potential of generating high-quality images, we …

2018-08-22abs ↗pdf ↗

Variational autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic properties from local regularities of natural language. Practically, however, VAEs with autoregressive decoders often suffer from posterior collapse, a phenomenon where the model l…

2019-11-10abs ↗pdf ↗