This review reports some key results in theoretical investigations on configurations of lipid membranes and presents several challenges in this field which involve (i) exact solutions to the shape equation of lipid vesicles; (ii) exact solutions to the governing equations of open lipid membranes; (iii) neck condition o…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “theoretical investigation”
This work builds a hedging mechanism for experimental risk.
problem Risk of financial and statistical bankruptcy in experimentation.
method Game-theoretic statistics framework, capitalization of test martingale wealth process, Markowitz portfolio theory, hedging instrument.
result Investigator can hedge against the null hypothesis and avoid ruin.
Paper assesses error estimates of Random Forests classification.
problem Quantitative assessment of Random Forests error estimates.
method Theoretical and empirical investigation of various error estimation methods.
result Random Forests' error estimates are closer to true error rate than average prediction error.
High order universal portfoliosq-fin.PM
New high-order universal portfolios outperform standard ones.
problem Improving upon the Cover universal portfolio.
method Constructing higher order universal portfolios by recurrence and analyzing their properties.
result Second high-order UP outperforms standard UP under perturbation.
Investigates training challenges for morphological neural networks.
problem Training morphological neural networks with gradient descent is difficult.
method Examines differentiation and backpropagation for morphological networks, using Bouligand derivative.
result Provides theoretical insights and guidelines for initialization and learning rates.
This work proves composite neural networks outperform their components under certain conditions.
problem Understanding the performance of composite neural networks.
method Theoretical investigation of a composite neural network combining pre-trained models.
result A composite neural network, with high probability, performs better than any of its pre-trained components.
We investigate index theory in the context of Dirac operators coupled to superconnections. In particular, we prove a local index theorem for such operators, and for families of such operators. We investigate eta-invariants and prove an APS-theorem, and construct a geometric determinant line bundle for families of such …
NCG methods improve shape optimization efficiency.
problem Shape optimization problems
method Nonlinear conjugate gradient methods
result NCG methods are efficient for shape optimization
A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstrationcs.CL
Theoretical work shows integrating coherent reasoning improves LLM performance and error correction.
problem Improving reasoning and error correction in large language models (LLMs) with few-shot prompting.
method Theoretical analysis and sensitivity experiments on transformer behavior with coherent reasoning and corrupted demonstrations.
result The transformer gains better error correction ability and more accurate predictions when coherent reasoning is integrated.
Paper analyzes how contrastive learning structures learned representations.
problem Understanding the structure of learned representations in contrastive learning.
method Kernel-based contrastive learning framework (KCL) and statistical dependency viewpoint.
result Theoretical upper bound and generalization error bound for KCL.
The paper provides a theoretical framework for machine learning.
problem Lack of rigorous theory guiding machine learning experiments.
method Bayesian statistics and Shannon's information theory.
result Theoretical insights applicable across various machine learning settings.
Paper analyzes self-supervised image denoising with denatured data.
problem Understanding the performance of self-supervised image denoising with denatured data.
method Theoretical analysis and numerical experiments on a denoising algorithm.
result Theoretical analysis shows the algorithm finds desired solutions to the optimization problem.
Beyond the Selected Completely At Random Assumption for Learning from Positive and Unlabeled Datacs.LG
Most positive and unlabeled data is subject to selection biases. The labeled examples can, for example, be selected from the positive set because they are easier to obtain or more obviously positive. This paper investigates how learning can be ena BHbled in this setting. We propose and theoretically analyze an empirica…
Study examines Lasso performance in high-dimensional MoE models.
problem Estimating MoE models in high-dimensional settings with Lasso.
method Investigates SGMoE models with Lasso regularization under mild assumptions.
result Provides non-asymptotic bounds for Lasso regularization parameter.
The grassmannian of hermitian lagrangian spaces in is a natural compactification of the space of hermitian matrices. We describe a Schubert-like, Whitney regular stratification on this space which has a Morse theoretic origin. We prove that these strata define closed subana…
New framework explains how larger pre-trained models reduce downstream learning sample complexity.
problem Understanding why larger pre-trained models reduce sample complexity in downstream tasks.
method Introducing a novel framework called Caulking inspired by PEFT methods.
result Improved pre-trained models provably decrease downstream task sample complexity.
Investigates optimal parameter allocation in Transformers for efficiency and expressivity.
problem Balancing expressivity and efficiency in Transformer model parameters.
method Mathematical analysis and theoretical characterization of attention heads and head dimensions.
result Later layers can operate more efficiently with reduced parameters due to saturation of softmax activations.
Deep nonlinear models pose a challenge for fitting parameters due to lack of knowledge of the hidden layer and the potentially non-affine relation of the initial and observed layers. In the present work we investigate the use of information theoretic measures such as mutual information and Kullback-Leibler (KL) diverge…
We theoretically and experimentally investigate tensor-based regression and classification. Our focus is regularization with various tensor norms, including the overlapped trace norm, the latent trace norm, and the scaled latent trace norm. We first give dual optimization methods using the alternating direction method …
We investigate the effect of the proportional hazards assumption on prognostic and predictive models of the survival time of patients suffering from amyotrophic lateral sclerosis (ALS). We theoretically compare the underlying model formulations of several variants of survival forests and implementations thereof, includ…
In this paper we study the problem of learning the weights of a deep convolutional neural network. We consider a network where convolutions are carried out over non-overlapping patches with a single kernel in each layer. We develop an algorithm for simultaneously learning all the kernels from the training data. Our app…
The paper investigates instance-based interpretation methods for VAEs.
problem Understanding how VAEs make predictions without supervision.
method Formally framed influence functions for VAEs and developed VAE-TracIn.
result Varying training samples significantly impacts VAE predictions.
Bounded rationality investigates utility-optimizing decision-makers with limited information-processing power. In particular, information theoretic bounded rationality models formalize resource constraints abstractly in terms of relative Shannon information, namely the Kullback-Leibler Divergence between the agents' pr…
This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at inference time. These techniques have proven effective in many contexts, but lack theoretical arguments. We close this gap by presenting a …
Paper quantifies label shift robustly.
problem Quantifying label shift in datasets.
method Robust estimators of label distribution.
result Maximum Likelihood Estimator is a robust estimator.
On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspectivecs.LG
NTK theory fails to predict practical behavior of large-width neural networks.
problem Theoretical limits of NTK do not match practical neural network architectures.
method Empirical investigation of NTK's applicability to large-width architectures.
result Practically relevant behavior of large-width architectures differs from NTK theory.
This paper investigates how data augmentation improves linear separation of manifold data.
problem Understanding how data augmentation enhances linear separation of manifold data.
method Investigates the conditions under which self-supervised representations can linearly separate multi-manifold data.
result Self-supervised learning can linearly separate manifolds with a smaller distance than unsupervised learning.
We present analytical investigations of a multiplicative stochastic process that models a simple investor dynamics in a random environment. The dynamics of the investor's budget, , depends on the stochasticity of the return on investment, , for which different model assumptions are discussed. The fat-tail d…
Study explores associated groups of symmetric quandles and their properties.
problem Understanding the structure and relationships of symmetric quandles and their associated groups.
method Group-theoretic analysis and characterization of associated groups.
result Characterization and properties of associated groups of symmetric quandles.
We briefly review a few aspects of the development of differential geometry which may be considered as being influenced by Einstein's general relativity. We focus on how Einstein's quest for a complete geometrization of matter and electromagnetism gave rise to an enormous amount of theoretical work both on physics and …
Empirical study shows consistent meta-RL algorithms adapt to OOD tasks.
problem Theoretical consistency of meta-RL algorithms and its practical implications.
method Empirical investigation of representative meta-RL algorithms, focusing on consistency and adaptation to out-of-distribution tasks.
result Theoretical consistent algorithms can adapt to OOD tasks, while inconsistent ones cannot, but can still fail for poor exploration.
A classical theorem due to Quillen (1969) identifies the unitary bordism ring with the Lazard ring, which classifies the universal one-dimensional commutative formal group law. We prove an equivariant generalization of this result by identifying the homotopy theoretic -equivariant unitary bordism ring, in…
By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests. However, the intrinsic mechanism for analyzing why such learning regimes can work has not been comprehensivel…
This paper explains the theoretical inductive bias of Isolation Forest.
problem Lack of theoretical foundation explaining Isolation Forest's success.
method Formulated the growth process of iForest as a random walk, derived expected depth function using transition probabilities.
result Established a theoretical understanding of iForest's effectiveness and parameter adaptability.
This article investigates a new gauge theoretic approach to Einstein's equations in dimension 4. Whilst aspects of the formalism are already explained in various places in the mathematics and physics literature, our first goal is to give a single coherent account of the theory in purely mathematical language. We then e…
Paper proposes a quantum deep clustering framework with improved performance.
problem Improving clustering performance in quantum machine learning.
method Quantum deep SVM, deep convolutional neural networks, and quantum K-Means clustering.
result The proposed quantum deep clustering framework shows significant performance gains over classical methods.
Study proposes worst+gap measure for better DG evaluation.
problem Lack of comprehensive exploration of average measure in DG evaluation.
method Introduced worst+gap measure and compared it with average measure.
result Worst+gap measure provides a more accurate approximation of true DG performance.
Investigates deep hedging under rough volatility models.
problem Performance of deep hedging framework under non-Markovian conditions.
method Analysis of rough volatility models, use of parsimonious network architectures.
result Parsimonious network architectures can capture non-Markovian time-series.
Proposes a new theoretical framework for PbRL that requires less human feedback.
problem Lack of theoretical work capturing practical PbRL frameworks.
method Introduces a reward-agnostic PbRL framework that acquires exploratory trajectories before human feedback.
result Demonstrates improved sample complexity for learning optimal policies in linear and low-rank MDPs.
Empirical investigation of a quantum field theory of forward ratescond-mat.stat-mech
A new test of a wide class of interest rate models is proposed and applied to a recently developed quantum field theoretic model and the industry standard Heath-Jarrow-Morton model. This test is independent of the volatility function unlike other tests previously proposed in the literature. It is found that the HJM mod…
Generative adversarial networks are a class of generative algorithms that have been widely used to produce state-of-the-art samples. In this paper, we investigate GAN to perform anomaly detection on time series dataset. In order to achieve this goal, a bibliography is made focusing on theoretical properties of GAN and …
Unified interpretation of softmax cross-entropy and negative sampling for knowledge graph embedding.
problem Lack of theoretical relationship between softmax cross-entropy and negative sampling loss functions in knowledge graph embedding.
method Used Bregman divergence to provide a unified interpretation of the two loss functions.
result Theoretical findings for fair comparison of softmax cross-entropy and negative sampling are derived.
In this work, we study generalized entropies and information geometry in a group-theoretical framework. We explore the conditions that ensure the existence of some natural properties and at the same time of a group-theoretical structure for a large class of entropies. In addition, a method for defining new entropies, u…
For a graph representation of a dataset, a straightforward normality measure for a sample can be its graph degree. Considering a weighted graph, degree of a sample is the sum of the corresponding row's values in a similarity matrix. The measure is intuitive given the abnormal samples are usually rare and they are dissi…
PRI-VAE learns disentangled representations by optimizing principle-of-relevant-information.
problem Learning disentangled representations under VAE framework remains unknown.
method Proposes PRI-VAE, a novel learning objective to optimize disentanglement.
result Demonstrates effectiveness of PRI-VAE on four benchmark datasets.
The paper investigates topic models, ensuring their statistical identifiability and accuracy.
problem Lack of formal theoretical investigation of topic model identifiability and estimation accuracy.
method Proposes a maximum likelihood estimator (MLE) based on integrated likelihood, introducing new geometric identifiability conditions.
result Introduces weaker conditions for topic model identifiability, allowing a broader investigation.
Study on infinite neural networks for generalization.
problem Understanding generalization in infinitely-wide neural networks.
method Analytical and empirical investigations of infinite ensembles.
result Signals correlating with generalization identified.
Study explores learning behavior of GFlowNets, revealing key mechanisms.
problem Lack of theoretical understanding of GFlowNets' learning dynamics.
method Rigorous theoretical investigation of four dimensions: convergence, sample complexity, implicit regularization, and robustness.
result Elucidates mechanisms underlying GFlowNet's learning dynamics, providing insights into performance factors.