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.

169,051 papers · 148 categories

Trend · papers per month

108217325433 · Jun 202019922001200920172026
48 results for high capacity

High-capacity neural network ensembles often benefit more from high-capacity models than from increased diversity.

problem The performance of high-capacity neural network ensembles is often harmed by interventions that promote predictive diversity.
method A large-scale study of nearly 600 neural network classification ensembles, examining various interventions and architectures.
result Discouraging predictive diversity can be benign in large-network ensembles, and higher-capacity models often yield better performance than diverse architectures.

A method decomposes battery cell capacity trends using MCGP for high accuracy and uncertainty.

problem Forecasting lithium-ion battery cells capacity with high accuracy and uncertainty.
method Multi-Output Convolved Gaussian Process (MCGP) for latent function decomposition.
result The MCGP method provides high prediction accuracy and uncertainty information.

Managing data storage growth is of crucial importance to businesses. Poor practices can lead to large data and financial losses. Access to storage information along with timely action, or capacity forecasting, are essential to avoid these losses. In addition, ensuring high accuracy of capacity forecast estimates along …

2018-12-01abs ↗pdf ↗

DNPUs improve neural network performance with high-capacity nanoelectronic nodes.

problem Limited performance of single DNPUs in solving complex classification problems.
method Developed DNPUs as high-capacity neurons and implemented multi-DNPU networks.
result Feed-forward DNPU networks improve single DNPU performance from 77% to 94% test accuracy.

Study characterizes memory capacity of quantum reservoirs using transmon qubits.

problem Understanding the memory capacity of quantum reservoirs built with transmon qubits.
method Characterized memory capacity of quantum reservoirs using transmon qubits from IBM, focusing on NMSE and topology complexity.
result Found a peak in memory capacity for configurations with n-1 self-loops, suggesting optimal design for forecasting tasks.

The brain optimizes memory by forgetting what's predictable, improving generalization.

problem Memory consolidation struggles with representational drift, semanticisation, and offline replay.
method Proposes predictive forgetting as a mechanism to optimize generalization by reducing complexity.
result Predictive forgetting improves information-theoretic generalization bounds on stored representations.

WGANs improve probability distribution approximation with depth and width trade-offs.

problem Approximating complex probability distributions accurately.
method Wasserstein GANs with GroupSort discriminators, quantified generalization bound.
result High-capacity discriminators are crucial for WGANs' performance.

The paper tackles imbalanced classification under operational constraints, proposing a framework to maximize sensitivity.

problem Detecting minority class observations under severe class imbalance and operational constraints.
method Formal classification framework under capacity constraints, maximizing sensitivity while respecting a user-defined label limit.
result The optimal classifier under capacity constraints is equivalent to the Bayes classifier with reweighted prior probabilities.

DEX allows HFTs to quickly acquire speed, improving price discovery without sacrificing liquidity.

problem Low-latency trading's externality and resource inefficiency in centralized exchanges.
method Model of decentralized exchanges with real-time speed acquisition from peer-to-peer networks.
result HFTs on DEX acquire more speed for shorter timespans, decreasing price discovery time and reducing resource lock-in.

The study improves the perceptron's storage capacity by optimizing variable selection.

problem Distinguishing genuine structure from random correlations in high-dimensional data.
method Replica method from statistical mechanics for optimal variable selection.
result Optimal variable selection can surpass the Cover--Gardner bound for pattern classification.

Convolutional neural networks predict the analytic rank of elliptic curves accurately.

problem Predicting the analytic rank of elliptic curves over Q.
method Applied one-dimensional convolutional neural networks to Frobenius traces.
result High accuracy predictions for analytic rank across various conductors.

New method lowers spherical perceptron capacity using fully lifted random duality theory.

problem Tackles the negative spherical perceptron capacity, a long-standing open problem.
method Develops fully lifted random duality theory (fl RDT) to characterize capacity.
result Shows remarkable closed-form analytical relations for practical capacity values.

New proof shows neural networks can memorize training data with high accuracy.

problem Proving neural networks can memorize training data with high accuracy.
method Probabilistic construction exploiting sparsity.
result Proves neural networks with threshold or mixed threshold-ReLU activations can memorize training data.

We study various capacities on compact Kähler manifolds which generalize the Bedford-Taylor Monge-Ampère capacity. We then use these capacities to study the existence and the regularity of solutions of complex Monge-Ampère equations.

2014-02-11abs ↗pdf ↗

Estimates graph process with high-frequency data, proving asymptotic properties.

problem Estimating graph process with high-frequency data.
method Discretized maximum likelihood estimators for GrOU process under high-frequency sampling.
result Asymptotic central limit theorems for estimators under finite and infinite jump activity.

Kernel networks' stability edge linked to Fisher Information singularity.

problem Understanding the stability edge in high-capacity kernel Hopfield networks.
method Statistical manifold analysis and Riemannian geometry.
result The Ridge of Optimization corresponds to the Edge of Stability, revealing a dual equilibrium.

Solves a discrete logarithmic Minkowski problem for electrostatic p-capacity.

problem Characterize measures generated by electrostatic p-capacity.
method Solves the discrete logarithmic Minkowski problem for 1 < p < n.
result Solves the discrete logarithmic Minkowski problem for measures in general position.

CapOptix uses options theory to price capacity in electricity markets.

problem Traditional capacity market designs fail to account for risk and price shocks.
method Interprets capacity commitments as reliability options and uses Markov Regime Switching Process.
result CapOptix provides more accurate pricing of capacity premia compared to existing mechanisms.

In this article, we propose the notion of the general pp-affine capacity and prove some basic properties for the general pp-affine capacity, such as affine invariance and monotonicity. The newly proposed general pp-affine capacity is compared with several classical geometric quantities, e.g., the volume, the pp-var…

2017-05-21abs ↗pdf ↗

Extends capacity analysis to neural networks, showing how capacity is distributed across layers.

problem How capacity is distributed in neural networks with non-linear layers.
method Introduces layer decoupling to quantify non-linear activation's impact, and uses a markovian rule for capacity propagation in deep networks.
result Shows that under certain conditions, capacity allocation in neural networks is equivalent to linear capacity allocation in an extended input space.

While symplectic manifolds have no local invariants, they do admit many global numerical invariants. Prominent among them are the so-called symplectic capacities. Different capacities are defined in different ways, and so relations between capacities often lead to surprising relations between different aspects of sympl…

2005-06-10abs ↗pdf ↗

Study excess capacity in neural networks using Rademacher complexity.

problem Understanding how much capacity deep networks have beyond what's needed for classification.
method Unified Rademacher complexity bounds for function composition and convolutional layers, considering Lipschitz constants and initialization norms.
result There is substantial excess capacity per task, and capacity can be kept similar across different tasks.

Improves VAE latent space by balancing capacity and disentanglement.

problem Hard to achieve both high capacity and disentanglement in VAE latent space.
method Formulates soft-constrained optimization problem to address both properties.
result EC and weight-filter method improve latent space quality and performance.

Study binary perceptrons' capacity using random duality theory.

problem Characterize the capacity of binary perceptrons with general thresholds.
method Utilized fully lifted random duality theory (fl RDT) to characterize the capacity.
result Characterizations match replica symmetry breaking predictions and uncover the capacity for zero-threshold scenario.

Matryoshka hides secret models in a carrier model, achieving high capacity and robustness.

problem Stealing functionality of private ML data by hiding models in a carrier model.
method Parameter sharing approach exploiting the learning capacity of the carrier model.
result Hides a 26x larger secret model or 8 secret models in the carrier model.

Study capacity constraints in continual learning with a simple model.

problem Understanding optimal resource allocation for agents with limited memory and compute resources.
method Analyzes a capacity-constrained linear-quadratic-Gaussian (LQG) sequential prediction problem and demonstrates optimal capacity allocation strategies.
result Derives a solution to the capacity-constrained LQG sequential prediction problem and shows how to optimally allocate capacity across sub-problems in the steady state.

Neural networks generalize well despite overfitting due to high capacity.

problem Understanding why deep neural networks generalize well in overparameterized settings.
method High-dimensional asymptotic analysis of generalization under kernel regression with Neural Tangent Kernel.
result Test error exhibits non-monotonic behavior and can have additional peaks and descents in the overparameterized regime.

New complete panel dataset for LMICs helps analyze innovation and development.

problem Lack of complete data for empirical analyses in LMICs.
method Predictive Mean Matching multiple imputation technique.
result Created a large dataset of 47 variables for 82 LMICs from 2005-2019.

Memory capacity of DAM scales exponentially with feature separation, unaffected by correlations.

problem Understanding how feature correlations impact DAM's capacity.
method Developed an empirical framework to analyze DAM's capacity under varying feature correlations and pattern separations.
result Memory capacity scales exponentially with feature separation, unaffected by correlations.

Proves local maximizers for higher Ekeland-Hofer capacities in 4D star-shaped domains.

problem Finding local maximizers for higher Ekeland-Hofer capacities in specific domains.
method Analogous to 4D local Viterbo conjecture, proving maximizers for rational ellipsoids.
result Local maximizers of the k-th Ekeland-Hofer capacities are symplectomorphic to rational ellipsoids.

The paper introduces capacity allocation analysis for neural networks, focusing on spatial capacity.

problem Designing neural network architectures is challenging due to the interplay of intuition, experimentation, and luck.
method Introduces capacity allocation analysis, focusing on spatial capacity allocation in linear settings.
result Quantitative comparison of classical architectures on various synthetic tasks reveals insights into model capacity allocation.

Derives an empirical capacity model for self-attention neural networks.

problem Theoretical capacity of large transformer models is not fully utilized by current optimization algorithms.
method Analyzes memory capacity of transformers using synthetic training data and common training algorithms.
result Derives an empirical capacity model (ECM) for a generic transformer.

Improves online learning algorithms for functional models with capacity assumptions.

problem Convergence rates of online stochastic gradient descent algorithms for functional linear models.
method Characterizations of slope function regularity, kernel space capacity, and sampling process covariance operator.
result Capacity assumptions can alleviate saturation of convergence rates as function regularity increases.