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.

168,694 papers · 148 categories

Trend · papers per month

144287431574 · Jun 202019922001200920172026
48 results for linear mode connectivity

The paper reveals surprising star-shaped connectivity in neural networks.

problem Understanding mode connectivity in neural network landscapes.
method Fine-grained analysis of connectivity in overparameterized and finite minima cases.
result Star-shaped connectivity exists in neural network landscapes, suggesting near convexity.

We consider the Yang-Mills flow on hyperbolic 3-space. The gauge connection is constructed from the frame-field and (not necessarily compatible) spin connection components. The fixed points of this flow include zero Yang-Mills curvature configurations, for which the spin connection has zero torsion and the associated R…

2012-10-02abs ↗pdf ↗

Proposes using mode connectivity to improve adversarial robustness of neural networks.

problem Improving adversarial robustness of deep neural networks.
method Employing mode connectivity in loss landscapes to study adversarial robustness and propose methods for improvement.
result Path connection learned using limited bonafide data can effectively mitigate adversarial effects while maintaining original accuracy.

For dynamical systems that can be modelled as asymptotically stable linear systems forced by Gaussian noise, this paper develops methods to infer or estimate their modes from observations in real time. The modes can be real or complex. For a real mode, we wish to infer its damping rate and mode shape. For a complex mod…

2019-09-23abs ↗pdf ↗

Improved modeling of chaotic systems using time-delay embeddings and Frenet-Serret frame.

problem Identifying effective coordinate systems for nonlinear dynamical systems.
method Developed a new algorithm to identify more stable and accurate models from less data, leveraging the connection between HAVOK and Frenet-Serret frame.
result The sub- and super-diagonal entries of the linear model correspond to intrinsic curvatures in Frenet-Serret frame.

Proposes neuron alignment to optimize mode connectivity in neural networks.

problem Understanding and optimizing mode connectivity in deep neural networks.
method Introduces neuron alignment to approximate optimal weight permutations and improve mode connectivity.
result Neuron alignment significantly alleviates robust loss barriers and improves model robustness and accuracy.

Proves analyticity of quasinormal modes in Kerr and Kerr-de Sitter spacetimes.

problem Analyticity of quasinormal modes in extreme Kerr and Kerr-de Sitter spacetimes.
method Observation of stable radial point source/sink structure in bicharacteristic flow; recent microlocal analysis result by Galkowski and Zworski.
result Quasinormal modes are real analytic in subextremal Kerr and Kerr-de Sitter spacetimes.

Mode clustering is a nonparametric method for clustering that defines clusters using the basins of attraction of a density estimator's modes. We provide several enhancements to mode clustering: (i) a soft variant of cluster assignment, (ii) a measure of connectivity between clusters, (iii) a technique for choosing the …

2014-06-06abs ↗pdf ↗

Paper discovers simplicial complexes connecting trained models for improved ensembling.

problem Improving robustness and accuracy of deep learning ensembles.
method Identifies mode-connecting simplicial complexes on loss surfaces.
result Efficiently builds simplicial complexes for ensembling, outperforming independent ensembles.

New method uses random projections to estimate densities and modes efficiently.

problem Estimating densities and modes from sparse representations.
method Expand-and-sparsify representations followed by linear function and mode recovery algorithms.
result Optimal rates for density and mode estimation achieved.

Empirical study shows removing neural parameter symmetries impacts model performance.

problem Understanding the impact of neural parameter symmetries on model performance.
method Developed two methods to reduce parameter space symmetries in neural networks.
result Removing parameter symmetries can lead to faster and more effective Bayesian neural network training.

LoRA-Curve connects independent LoRA optima through continuous low-loss valleys, improving Bayesian model averaging.

problem Challenges in estimating epistemic uncertainty in LoRA-based Bayesian inference.
method Introduces LoRA-Curve, a segmented Bézier curve parameterization in the LoRA space, with free and anchored configurations.
result Empirically shows that connecting independent LoRA optima through continuous low-loss valleys improves mutual information of the predictive distribution.

Study identifies failure modes of machine learning models in out-of-distribution settings.

problem Machine learning models fail to generalize well to new, unseen data.
method Theoretical study of gradient-descent-trained linear classifiers on easy-to-learn tasks, followed by experiments on modern neural networks.
result Two failure modes of spurious correlations are uncovered: geometric and statistical.

We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode, exploding/vanishing mean activation length, can be avoided by initializing weights from a …

2018-03-05abs ↗pdf ↗

Study on stability of 3D sessile drops, identifying degenerate kernel.

problem Linear stability of three-dimensional sessile drops with a free contact line.
method Derived constrained second variation, formulated Jacobi problem, combined geometric and Fourier analysis.
result Kernel of the constrained Jacobi operator is exactly the space of horizontal translations under pressure-volume nondegeneracy.

Optimized DMD for fast atmospheric chemistry forecasting.

problem Forecasting global atmospheric chemistry dynamics efficiently.
method Optimized Dynamic Mode Decomposition (DMD) for reduced order modeling.
result Significant improvement in computational speed and interpretability.

AutoLL uses neural networks to automatically reorder graph nodes for linear layouts.

problem Finding optimal node order in adjacency matrices without predefined features.
method Developed AutoLL-D and AutoLL-U neural network models for one-mode reordering of directed and undirected graphs.
result Demonstrated effectiveness of AutoLL through qualitative and quantitative evaluations.

Proposes MVGPR for spatiotemporal data modal analysis.

problem Sparse and irregularly sampled data in complex flows.
method Multivariate Gaussian process regression (MVGPR) with kernel design.
result MVGPR outperforms DMD and SPOD in modal analysis of sparse and irregular data.

pLSTM tackles long-range language modeling and computer vision tasks with parallelizable linear source transition mark networks.

problem Challenges of existing recurrent architectures in handling sequences and multi-dimensional data.
method Introduces pLSTM, a parallelizable linear source transition mark network for linear graphs and DAGs, addressing vanishing/exploding activation/gradient issues.
result pLSTM outperforms Transformers in long-range tasks like arrow-pointing extrapolation and image size extrapolation.

Multimodal clustering is an unsupervised technique for mining interesting patterns in nn-adic binary relations or nn-mode networks. Among different types of such generalized patterns one can find biclusters and formal concepts (maximal bicliques) for 2-mode case, triclusters and triconcepts for 3-mode case, closed $n…

2017-02-27abs ↗pdf ↗

Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes. We consider two such models: the switching linear dynamical system (SLDS) and the switching vector autoregressive (VAR) process. Our Bayesian nonparametric approach utilizes a hiera…

2010-03-19abs ↗pdf ↗

New method decomposes KL error using refined information and mode interactions.

problem Learning probability distributions over discrete variables with higher-order interactions.
method Using information geometry, refined mode interactions, and a novel Monte-Carlo sampling technique.
result Complete decomposition of KL error and efficient data use.

We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that standard vision models become stable to SGD noise in this way early in training. From then on, the outcome of optimization is determined to a …

2019-12-11abs ↗pdf ↗

Finsler geometry connects to higher-spin fields and curved-space Fronsdal equations.

problem Eliminating non-transverse modes in Finsler dynamics for higher spins.
method Parameterizing Finsler geometry in terms of symmetric tensors, analyzing linear and nonlinear terms, and examining gauge transformations.
result Finsler dynamics leads to the curved-space Fronsdal equation for all spins, plus a Stueckelberg-like coupling.

Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little divers…

2017-12-12abs ↗pdf ↗

Many generative models have to combat missing modes\textit{missing modes}. The conventional wisdom to this end is by reducing through training a statistical distance (such as ff-divergence) between the generated distribution and provided data distribution. But this is more of a heuristic than a guarantee. The statistical distanc…

2019-02-13abs ↗pdf ↗

Mode connectivity is a recently introduced frame- work that empirically establishes the connected- ness of minima by finding a high accuracy curve between two independently trained models. To investigate the limits of this setup, we examine the efficacy of this technique in extreme cases where the input models are trai…

2018-06-18abs ↗pdf ↗

Proves wave equation solutions in Kerr-de Sitter spacetime have specific asymptotic expansions.

problem Analyzing solutions to wave equations in Kerr-de Sitter spacetime.
method Developed a Fredholm setup for quasinormal modes and analyzed trapping of lightlike geodesics.
result Proves asymptotic expansions of wave equation solutions up to a decay order.

Reduced modeling in high-dimensional reproducing kernel Hilbert spaces offers the opportunity to approximate efficiently non-linear dynamics. In this work, we devise an algorithm based on low rank constraint optimization and kernel-based computation that generalizes a recent approach called "kernel-based dynamic mode d…

2020-02-11abs ↗pdf ↗

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test accuracy are nearly constant. We introduce a training procedure to discover these hig…

2018-02-27abs ↗pdf ↗

This paper characterizes VAE training pathologies and their effects on tasks.

problem Characterizing VAE training pathologies and their impact on downstream tasks.
method Concretely characterizing conditions for VAE training pathologies and their connection to specific downstream tasks.
result Connects VAE training pathologies to specific downstream tasks like learning compressed and disentangled representations, adversarial robustness, and semi-supervised learning.