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.
Many state-of-the-art results obtained with deep networks are achieved with the largest models that could be trained, and if more computation power was available, we might be able to exploit much larger datasets in order to improve generalization ability. Whereas in learning algorithms such as decision trees the ratio …
We improve deep threshold networks' memorization capacity exponentially.
problem Memorizing datasets with randomized labels using deep neural networks.
method Using Gaussian random weights in the first layer and binary or integer weights in subsequent layers, we prove a new dependence on minimum distance.
result We show that O(δ1+n) neurons and O(δd+n) weights are sufficient.
Expressive efficiency refers to the relation between two architectures A and B, whereby any function realized by B could be replicated by A, but there exists functions realized by A, which cannot be replicated by B unless its size grows significantly larger. For example, it is known that deep networks are exponentially…
TTERGM models improve social network predictions by incorporating triadic relationships.
problem Lack of models capturing triadic relationships and social learning theories in temporal network data.
method Introduced TTERGM, a generative model that includes triadic relationships and social learning theory as additional probability distributions. Parameters are estimated via Monte Carlo maximum likelihood.
result TTERGM achieves improved accuracy and fidelity compared to existing models on social network data.
In this work, an ensemble of economic interacting agents is considered. The agents are arranged in a linear array where only local couplings are allowed. The deterministic dynamics of each agent is given by a map. This map is expressed by two factors. The first one is a linear term that models the expansion of the agen…
An array system of coupled maps is proposed as a model for economy evolution. The local dynamics of each map or agent is controlled by two parameters. One of them represents the growth capacity of the agent and the other one is a control term representing the local environmental pressure which avoids an exponential gro…
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.
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…
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…
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.
Quantum LS-SVM simplifies matrix inversion for faster machine learning.
problem Speeding up machine learning algorithms for large datasets.
method Introduces a novel quantum algorithm using continuous variables to simplify matrix inversion in LS-SVM, and proposes a hybrid quantum-classical approach for sparse solutions.
result Quantum LS-SVM achieves exponential speed-up and can solve classically difficult tasks.
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.
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…
Study relates symplectic homology capacity to periodic orbits in Liouville domains.
problem Relating symplectic homology capacity to periodic orbits in Liouville domains.
method Uses positive symplectic homology and Hofer-Zehnder capacity to establish bounds and existence of periodic points.
result Non-zero positive symplectic homology implies finite upper bound for Hofer-Zehnder capacity relative to skeleton and Hamiltonian diffeomorphisms.
Estimates the capacity of face representations, providing upper bounds for automatic face recognition.
problem Estimating how many identities a face representation can resolve.
method Formulated as packing bounds on a low-dimensional manifold embedded in a deep representation space, accounting for manifold structure and noise.
result Demonstrated upper bounds of 2.7×10^4 and 8.4×10^4 for FaceNet and SphereFace at a FAR of 1%, respectively.