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

4007991,1991,598 · Jun 202019922001200920172026
48 results for model complexity

While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform, and studies have shown a potentially richer representation of complex nets. In …

2019-10-22abs ↗pdf ↗

New measure shows various training techniques control model complexity.

problem Understanding how to control model complexity in deep learning.
method Developed geometric complexity measure and demonstrated its effectiveness.
result Many training techniques control geometric complexity, providing a unified framework.

We consider computational complexity of problems related to the fundamental group and the first homology group of (embeddable) 22-complexes. We show, as an extension of an earlier work, that computing first homology of 22-complexes is equivalent in computational complexity to matrix diagonalization. That is, the usua…

2015-12-16abs ↗pdf ↗

Paper proposes LANN to measure model complexity of neural networks with curve activation functions.

problem Measuring model complexity of neural networks with curve activation functions.
method Proposes LANN, a piecewise linear framework to approximate curve activation functions, and derives complexity measure based on the number of linear regions.
result Demonstrates positive correlation between overfitting and model complexity during training.

Modeling structure in complex networks using Bayesian non-parametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data. This paper provides a gentle introduction to non-parametric Bayesian modeling of complex networks: Using an infinite mixture model …

2013-12-20abs ↗pdf ↗

Proposes a new complex Gaussian distribution for better modeling of complex-valued signals.

problem Limited ability of Gaussian distribution to represent diverse amplitude characteristics.
method Introduces a power-weighted noncentral complex Gaussian distribution on the complex plane.
result Consistently outperforms conventional distributions in log-likelihood for speech power spectra.

Measures neural network complexity via effective degrees of freedom.

problem Challenges in quantifying neural network complexity.
method Adapts generalized degrees of freedom (GDF) for binary outcomes and compares with cross-validation and null degrees of freedom.
result GDF provides a robust measure of model complexity for neural networks.

Diffusion models learn simple statistics before complex ones, revealing a sample complexity exponent.

problem Understanding the learning dynamics of diffusion models.
method Empirical observations and theoretical analysis of diffusion models and denoisers.
result Diffusion models learn simple statistics (pair-wise correlations) at linear sample complexity, while higher-order statistics (e.g., fourth cumulant) require cubic sample complexity.

Advances combinatorial complexes for better modeling of hierarchical and set-type relations.

problem Lack of effective modeling for complex hierarchical and set-type relations in high-dimensional data.
method Introduces combinatorial complexes as a bridge between cell complexes and hypergraphs, emphasizing their different types of relations.
result Combining set-type and hierarchical relations in a single model can be advantageous in learning tasks.

Proposes Neural Complexity (NC) for predicting and explaining generalization in deep neural networks.

problem Challenges in specifying a suitable complexity measure for deep neural networks to predict and explain generalization.
method A meta-learning framework that learns a scalar complexity measure through interactions with many heterogeneous tasks.
result Trained NC model can be added to standard training loss to regularize any task learner.

CVRL tackles complex visual observations in reinforcement learning.

problem Complex visual observations in natural environments.
method Contrastive Variational Reinforcement Learning (CVRL) learns a contrastive variational model by maximizing mutual information between latent states and observations.
result CVRL achieves comparable performance with state-of-the-art model-based DRL methods and significantly outperforms them on tasks with complex observations.

Paper introduces a new edge exchangeable block model for complex networks.

problem Limitations of the stochastic block model in analyzing complex networks.
method Develops a Bayesian nonparametric edge exchangeable block model.
result The new model outperforms state-of-the-art SBMs for link prediction.

Double descent in portfolio optimization shows improved performance with complexity, then declines, due to overfitting.

problem Improving portfolio optimization performance with model complexity.
method Investigates the relationship between model complexity and out-of-sample performance in mean-variance portfolio optimization.
result Performance of low-dimensional models initially improves with complexity but declines due to overfitting. High-dimensional models show double ascent Sharpe ratio curve.

Rectified flows achieve optimal sample complexity for generating data.

problem Generating high-quality data samples efficiently.
method Rectified flows constrain transport trajectories to be linear, enabling efficient sampling.
result Achieve sample complexity of ildeO(ε2) ilde{O}(\varepsilon^{-2}), matching optimal rate for mean estimation.

Improved sample complexity for training diffusion models.

problem How many samples are needed to train an accurate diffusion model?
method Analyzing the sample complexity of training diffusion models using neural networks.
result Exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other parameters.

Study Bernstein-Gelfand-Gelfand complexes on Lipschitz domains, computing cohomology and applying to elasticity models.

problem Cohomology of BGG complexes on bounded Lipschitz domains.
method Computes cohomology of conformal deformation and Hessian complexes in Sobolev spaces, allowing multiple input complexes.
result Establishes conformal Korn inequality and proposes generalizations of continuum models with microstructures.

Examines algorithmic modeling across three cultures.

problem Tackles algorithmic modeling in different cultural contexts.
method Uses parametric regressions, interpretable algorithms, and complex algorithms.
result Extension of Leo Breiman's thesis to include cultural differences.

New model-free DR-RL algorithm with finite sample complexity.

problem Limited model-free DR-RL methods with convergence guarantees or sample complexities.
method Integrates Multi-level Monte Carlo (MLMC) technique with threshold mechanism.
result First model-free DR-RL approach with finite sample complexity for total variation and Chi-square divergence.

We give nearly matching upper and lower bounds on the oracle complexity of finding εε-stationary points (F(x)ε\| \nabla F(x) \| \leqε) in stochastic convex optimization. We jointly analyze the oracle complexity in both the local stochastic oracle model and the global oracle (or, statistical learning) model. This allows u…

2019-02-13abs ↗pdf ↗

Optimal sample complexity for learning Gaussian DAG models established.

problem Learning the structure of Gaussian DAG models from observational data.
method Established minimax optimal sample complexity for two settings: equal variances without ordering knowledge and general linear models with ordering knowledge.
result Optimal sample complexity nqlog(d/q)n\asymp q\log(d/q) for both settings, matching undirected graphical models under equal variances.

Improved sample complexity for Gaussian Mixture Models using Pair Correlation Factor.

problem Understanding the sample complexity of Gaussian Mixture Models.
method Introducing Pair Correlation Factor (PCF) to measure clustering of component means and improving sample complexity bounds.
result The Pair Correlation Factor (PCF) more accurately determines the difficulty of parameter recovery in Gaussian Mixture Models.

A representative investor generates realistic and complex security price paths by following this trading strategy: if, a few ticks ago, the market asset had two consecutive upticks or two consecutive downticks, then sell, and otherwise buy. This simple, unique, and robust model is the smallest possible deterministic mo…

2009-01-24abs ↗pdf ↗

We find a worldsheet realization of generalized complex geometry, a notion introduced recently by Hitchin which interpolates between complex and symplectic manifolds. The two-dimensional model we construct is a supersymmetric relative of the Poisson sigma model used in context of deformation quantization.

2004-05-10abs ↗pdf ↗

Proposes a new prior for complex models to improve prediction accuracy.

problem Difficulty in specifying priors for complex models like neural networks.
method Predictive complexity priors defined by comparing model predictions to a reference model, transferred to parameters via change of variables.
result Improves model predictions by reducing unintuitive effects of traditional priors.

PolarBM models complex-valued audio signals in polar coordinates, improving over conventional methods.

problem Discarding structural information in complex-valued problems simplifies models but loses important amplitude-phase relationships.
method Proposes PolarBM, a novel Boltzmann machine for complex-valued variables in polar coordinates, and LogPolarBM for logarithmic amplitude.
result PolarBM and LogPolarBM achieve superior modeling accuracy compared to conventional models, including deep neural networks.

New method reduces sample complexity for learning Ising model dynamics exponentially.

problem Learning binary graphical models from correlated samples produced by a dynamical process.
method Two estimators based on interaction screening objective and conditional likelihood loss.
result Sample complexity reduces exponentially for samples from a dynamical process far from equilibrium.

GTMs model complex multivariate data with varying conditional independencies.

problem Modeling multivariate data with intricate marginals and complex dependency structures.
method Semiparametric approach using penalized splines and lasso regularization.
result GTMs accurately learn complex dependencies and identify conditional independencies.

New analysis shows transfer learning can significantly reduce sample size for complex models.

problem Reducing sample size needed for complex models like large language models.
method Optimal transport viewpoint applied to analyze transfer learning efficiency.
result Transfer learning can achieve better sample efficiency for complex models.

This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.

problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.

The paper explores how invertibility affects the complexity of encoder models in VAEs.

problem The complexity of the encoder model in VAEs when the generative map is invertible.
method Formalizes the concept of strong invertibility and analyzes the complexity of the encoder model.
result Strongly invertible generative maps allow for simpler encoder models, while non-invertible maps require exponentially larger encoders.