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.
New method addresses crowding in high-dimensional data visualization.
problem Crowding issue in visualizing high-dimensional data.
method Adjusting capacity of high-dimensional balls and estimating correlation dimension.
result Mitigates crowding in various distance metrics.
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.
SteganoGAN hides data in images with high capacity and high quality.
problem Hiding secret messages in images without detection.
method Generative adversarial networks (GANs) to optimize image quality and payload size.
result Achieves 4.4 bits per pixel payload, evades steganalysis, works on multiple datasets.
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 …
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.
Model for cross-border markets with limited transmission capacities.
problem Limited transmission capacities between two countries' markets.
method Developed a regime-switching process model with high-frequency approximation.
result Analytic tractability allows computation of key market quantities.
Adaptive Divergence speeds up AO for heavy generators.
problem Training high-capacity models on generators is computationally expensive.
method Introduces a novel family of divergences that vary model capacity.
result Significant acceleration in AO tasks with reduced computational costs.
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.
Enhances neural network dynamics to boost computational capacity.
problem Improving computational capacity of neural networks.
method Introducing Phase Transition Adaptation to drive system dynamics towards edge of stability.
result Consistently achieves enhancement in computational capacity over multiple datasets.
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.
Improves GAN sample quality by refining the training dataset.
problem GANs generate unrealistic samples outside the data manifold.
method Instance selection to improve sample quality and reduce training time.
result Significantly reduces training time and improves sample fidelity.
DDN dynamically combines weights for domain-specific models, improving performance.
problem Limited compute resources for edge devices.
method Domain-aware Dynamic Network (DDN) that combines specialized weights based on input domain.
result DDN achieves up to 2.6% higher AP50 than a static network on the BDD100K benchmark.
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.
Data selection boosts fact memorization in language models.
problem Language models struggle to accurately memorize factual knowledge.
method Formalizes fact memorization, proposes data selection schemes based on training loss.
result Data selection boosts fact accuracy to model capacity and improves performance.
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.
Study proposes managing COVID-19 without economy shutdowns.
problem Avoiding lockdowns while maintaining healthcare system capacity.
method Detailed heterogeneous epidemiological model, calibrated to data.
result Countries can avoid lockdowns if ICU beds per million > 100.
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.
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 p-affine capacity and prove some basic properties for the general p-affine capacity, such as affine invariance and monotonicity. The newly proposed general p-affine capacity is compared with several classical geometric quantities, e.g., the volume, the p-var…
Complexity helps identify sparse risk factors in asset pricing.
problem Tension between feature richness and economic parsimony in high-dimensional asset pricing.
method Expanding feature space and using basis pursuit to discover sparse risk factors.
result Nonlinear feature expansions combined with basis pursuit yield superior out-of-sample performance.
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.
Millimeter Wave (MmWave) communication is one of the key technology of the fifth generation (5G) wireless systems to achieve the expected 1000x data rate. With large bandwidth at mmWave band, the link capacity between users and base stations (BS) can be much higher compared to sub-6GHz wireless systems. Meanwhile, due …
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…
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 rigidity by logarithmic capacity and related functions.
problem Rigidity phenomena in kernel functions and capacities.
method Exploration of Bergman kernel, logarithmic capacity, Green's function, and Euclidean distance/volume.
result Established rigidity theorems by logarithmic capacity.
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.
Upper bounds for Lagrangian capacities of Liouville domains
problem Lagrangian capacity of Liouville domains
method Using S1-equivariant techniques result Extremal Lagrangian torus on the boundary of ellipsoid
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.
The real estate is a pillar industry of China's national economy. Due to changes in policy and market conditions, the real estate companies are facing greater pressures to survive in a competitive environment. They must improve their financial competitiveness. Based on the conceptual framework of financial competitiven…
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.
Develops a theory for mth order p-affine capacity for convex bodies containing the origin.
problem Defines and studies the mth order p-affine capacity for convex bodies containing the origin.
method Provides equivalent definitions, proves properties, and establishes inequalities.
result Establishes inequalities comparing to other geometric measures.
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.