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.
New measure FTC quantifies how much a ReLU network can fine-tune.
problem Analyzing memorization capacity in fine-tuned neural networks.
method Defined Fine-Tuning Capacity (FTC) for additive fine-tuning of ReLU networks.
result Upper and lower bounds on FTC for 2 and 3-layer ReLU networks.
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.
We study the computational capacity of a model neuron, the Tempotron, which classifies sequences of spikes by linear-threshold operations. We use statistical mechanics and extreme value theory to derive the capacity of the system in random classification tasks. In contrast to its static analog, the Perceptron, the Temp…
We introduce the concept of pseudo symplectic capacities which is a mild generalization of that of symplectic capacities. As a generalization of the Hofer-Zehnder capacity we construct a Hofer-Zehnder type pseudo symplectic capacity and estimate it in terms of Gromov-Witten invariants. The (pseudo) symplectic capacitie…
New method uses relative capacities of geodesic balls to determine scalar curvature.
problem Determining scalar curvature from geodesic ball volumes.
method Using relative capacities of concentric small geodesic balls.
result Scalar curvature is determined by relative capacities of geodesic balls.
Optimizes insurance processing capacity to minimize costs.
problem Processing delays and backlogs in insurance claims.
method Optimal capacity selection to minimize delay-adjusted and fixed costs.
result Minimizes claims costs by balancing processing capacity and delays.
Normalization layers control deep neural network capacity, improving stability and generalization.
problem Excessive capacity in deep neural networks leads to overfitting and poor generalization.
method Developed a theoretical framework to explain normalization's role in capacity control.
result Normalization layers reduce the Lipschitz constant exponentially, smoothing the loss landscape and enhancing generalization.
New analysis shows capacity of treelike neural networks with various activations.
problem Analyzing the capacity of treelike neural networks with diverse activations.
method Utilized Random Duality Theory and its partially lifted version to handle various activations.
result The capacity of treelike neural networks decreases for large network width but converges to a constant value.
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 …
Learning capacity measures model complexity, correlating with test loss and sample size.
problem Understanding model complexity and its relation to test performance.
method Formal correspondence between thermodynamics and inference; learning capacity as a measure of effective dimensionality.
result Learning capacity correlates with test loss and is a small fraction of model parameters.
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.
A variety of large-scale machine learning problems can be cast as instances of constrained submodular maximization. Existing approaches for distributed submodular maximization have a critical drawback: The capacity - number of instances that can fit in memory - must grow with the data set size. In practice, while one c…
The electric capacity of a conductor in the 3-dimensional Euclidean space R3 is defined as a ratio of a given positive charge on the conductor to the value of potential on the surface. This definition of the capacity is independent of the given charge. The capacity of a set as a mathematical notion was defined firs…
Deep imagination optimizes decision-making in large trees with limited resources.
problem Optimal planning in large decision trees with limited resources and time.
method Analytical solutions and numerical analysis of sampling capacity allocation.
result Optimal policy is to allocate few samples per level for deep exploration, favoring depth over breadth.
We use drifted Brownian motion in warped product model spaces as comparison constructions to show p-hyperbolicity of a large class of submanifolds for p≥2. The condition for p-hyperbolicity is expressed in terms of upper support functions for the radial sectional curvatures of the ambient space and for the rad…
gLSTM improves graph neural networks by increasing storage capacity to prevent over-squashing.
problem Over-squashing in GNNs collapses information from a large receptive field into a single vector, creating an information bottleneck.
method Introduced a new synthetic task to measure over-squashing and adapted ideas from sequence modeling to develop gLSTM, a novel GNN architecture with improved capacity.
result gLSTM architecture demonstrates strong performance on synthetic and real-world graph benchmarks, mitigating over-squashing.
Adding noise controls capacity of function compositions.
problem Large capacity of function compositions with bounded capacity classes.
method Adding Gaussian noise to the output of F before composing with H. result Noise effectively controls the capacity of H∘F, offering a general recipe for modular design. Modeling alignment as resource-limited cognitive processes, researchers derive performance bounds.
problem Systematic deviations in feedback-based alignment of large language models.
method Modeling alignment as a two-stage cascade UoHoY given S, with cognitive and total capacities. result Capacity-coupled Alignment Performance Interval derived from Fano and PAC-Bayes bounds.
The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active on a per-example basis, has been proposed in theory as a way of dramatically increasing model capacity without a proportional increase in computation. In practice…
We investigate under and overfitting in Generative Adversarial Networks (GANs), using discriminators unseen by the generator to measure generalization. We find that the model capacity of the discriminator has a significant effect on the generator's model quality, and that the generator's poor performance coincides with…
Rectified Linear Units (ReLU) have become the main model for the neural units in current deep learning systems. This choice has been originally suggested as a way to compensate for the so called vanishing gradient problem which can undercut stochastic gradient descent (SGD) learning in networks composed of multiple lay…
Scalable Gaussian process models trained with unbiased stochastic ELBO.
problem Training large capacity Gaussian process models on huge datasets.
method Unbiased stochastic variational inference for scalable GPs.
result Accurate inference on large datasets with up to 10 million basis functions.
New study shows how model complexity affects test risk, challenging classical theory.
problem Understanding how test risk scales with model complexity for large over-parametrized deep networks.
method Developed norm-based capacity measures for random features based estimators, providing precise characterization of estimator's norm concentration and test error.
result Predicted learning curve shows a phase transition from under- to over-parameterization, confirming classical U-shaped behavior with appropriate capacity measures.
Following the recent work on capacity allocation, we formulate the conjecture that the shattering problem in deep neural networks can only be avoided if the capacity propagation through layers has a non-degenerate continuous limit when the number of layers tends to infinity. This allows us to study a number of commonly…
Reservoir computing's success depends on mapping different input time series to separable states.
problem Quantifying the ability of random linear reservoirs to map different input time series.
method Mathematical framework using spectral properties of the connectivity matrix.
result Separation capacity is fully characterized by the spectral properties of the connectivity matrix.
ChatGPT predicts stock market reactions from news headlines without financial training.
problem Predicting stock price movements using non-financial data.
method Used post-knowledge-cutoff headlines to train ChatGPT-4, which forecasts stock market reactions.
result ChatGPT-4 can predict stock market reactions with high accuracy, especially for small stocks and negative news.
Paper tackles inventory management with deep learning, improving performance and adherence to constraints.
problem Managing inventory with limited resources and constraints.
method Proposes a novel method to sample from a distribution of possible constraint paths, extends exo-IDP formulation, introduces neural coordinator, and uses modified DirectBackprop algorithm.
result Deep reinforcement learning policies with a neural coordinator outperform classic baselines in terms of performance and adherence to constraints.
Wide neural networks can degrade performance, contrary to conventional wisdom.
problem Understanding the limitations of increasing network width in neural networks.
method Using Deep Gaussian Processes to decouple capacity and width, analyzing their effects on representational power and non-Gaussianity.
result Wide neural networks can become less adaptable and more Gaussian, leading to performance degradation.
Study on Privileged ERM showing limitations and providing capacity analysis.
problem Improving classification accuracy with privileged information.
method Theoretical analysis of Privileged ERM using VC dimension and generalization bounds.
result Worst-case guarantees for Privileged ERM cannot improve over standard ERM unless privileged information capacity is similar or smaller.
Proposes unbiased estimators for training mixture of experts models.
problem Efficiently training large-scale mixture of experts models on modern hardware.
method Two unbiased estimators based on principled stochastic assignment procedures.
result Both estimators are more effective and robust than biased alternatives.
New complexity measure helps in agnostic reinforcement learning with or without access to MDP dynamics.
problem Understanding the number of rounds needed to learn an ε-suboptimal policy in unknown MDPs.
method Introducing spanning capacity as a new complexity measure and developing POPLER algorithm.
result There is a separation between generative and online access models for agnostic learnability.
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.
We study the geometric flow of a planar curve driven by its curvature and the normal derivative of its capacity potential. Under a convexity condition that is natural to our problem, we establish long term existence and large time asymptotics of this flow.
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.
Unweighted matrix factorization can match or outperform weighted methods in recommender systems.
problem Improving recommendation performance with matrix factorization on implicit feedback data.
method Systematic study of various weighting schemes and matrix factorization algorithms.
result Training with unweighted data can perform comparably to, and sometimes outperform, training with weighted data.
New analysis shows over-squashing limits GNNs' power.
problem Understanding the expressive power of GNNs, especially under over-squashing.
method Quantitative measure of pairwise interactions in MPNNs, proving capacity requirements.
result Over-squashing hinders GNNs' ability to learn complex node feature functions.
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.
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.
Optimizes query routing to LLMs under cost and resource constraints.
problem Non-uniform or adversarial batching in per-query routing methods leads to cost inefficiency.
method Batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch.
result Robust routing framework improves accuracy by 1-14% over non-robust methods.
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…
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.
Study optimal treatment assignment policies under strategic agent responses.
problem Learning optimal treatment policies with strategic agents complicates estimation.
method Dynamic model with threshold convergence to mean-field equilibrium, consistent estimator for policy gradient.
result Threshold for treatment assignment converges to mean-field equilibrium threshold under large but finite number of agents.
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.
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.