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.
Study freezing sets for digital images in a 2D grid.
Study minimal freezing sets in convex digital disks.
New method for freezing sets in arbitrary dimensions.
Study on cold and freezing sets in digital images.
We introduce a local move on a link diagram named a region freeze crossing change which is close to a region crossing change, but not the same. We study similarity and difference between region crossing change and region freeze crossing change.
New tools for constructing fixed point sets in digital topology.
New method finds compact strong lottery tickets in partially frozen networks.
Examines how irreducibility and rigidity affect digital images.
Survey on reducing deep neural network training complexity.
Find limiting sets for digital cones and suspensions.
Improved off-policy selection and learning in contextual bandits with better guarantees.
Freezing of gait (FoG) is a common gait disability in Parkinson's disease, that usually appears in its advanced stage. Freeze episodes are associated with falls, injuries, and psychological consequences, negatively affecting the patients' quality of life. For detecting FoG episodes automatically, a highly accurate dete…
Simple fine-tuning of GANs with frozen discriminator outperforms existing methods.
In this paper we develop a dynamic form of Bayesian optimization for machine learning models with the goal of rapidly finding good hyperparameter settings. Our method uses the partial information gained during the training of a machine learning model in order to decide whether to pause training and start a new model, o…
The early layers of a deep neural net have the fewest parameters, but take up the most computation. In this extended abstract, we propose to only train the hidden layers for a set portion of the training run, freezing them out one-by-one and excluding them from the backward pass. Through experiments on CIFAR, we empiri…
Model shows bailout stigma affects firm funding and market performance.
We study the effect of liquidity freezes on an economic agent optimizing her utility of consumption in a perturbed Black-Scholes-Merton model. The single risky asset follows a geometric Brownian motion but is subject to liquidity shocks, during which no trading is possible and stock dynamics are modified. The liquidity…
Enhances swaption modeling with rough stochastic volatility.
Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explainable Artificial Intelligent, this paper proposes a novel technique called Auto DeepVis to dissect c…
Over the last few years, Deep Neural Networks (DNNs) have become ubiquitous owing to their high accuracy on real-world tasks. However, this increase in accuracy comes at the cost of computationally expensive models leading to higher prediction latencies. Prior efforts to reduce this latency such as quantization, model …
Centered Kernel Alignment (CKA) was recently proposed as a similarity metric for comparing activation patterns in deep networks. Here we experiment with the modified RV-coefficient (RV2), which has very similar properties as CKA while being less sensitive to dataset size. We compare the representations of networks that…
SOR framework improves transfer learning efficiency and adaptability.
We continue the work of [10], studying properties of digital images determined by fixed point invariants. We introduce pointed versions of invariants that were introduced in [10]. We introduce freezing sets and cold sets to show how the existence of a fixed point set for a continuous self-map restricts the map on the c…
Analyzes how financial network dependencies can lead to multiple equilibrium outcomes and optimal bailout strategies.
Some tasks, such as surface normals or single-view depth estimation, require per-pixel ground truth that is difficult to obtain on real images but easy to obtain on synthetic. However, models learned on synthetic images often do not generalize well to real images due to the domain shift. Our key idea to improve domain …
Paper explores BERT's efficiency on SQuAD2.0, freezing layers and using adapters.
Survey examines types of systemic risk in financial networks.
ICE-Pruning accelerates deep neural network pruning by 9.61x.
We examine in this article the pricing of target volatility options in the lognormal fractional SABR model. A decomposition formula by Ito's calculus yields a theoretical replicating strategy for the target volatility option, assuming the accessibilities of all variance swaps and swaptions. The same formula also sugges…
We apply results of Malliavin-Thalmaier-Watanabe for strong and weak Taylor expansions of solutions of perturbed stochastic differential equations (SDEs). In particular, we work out weight expressions for the Taylor coefficients of the expansion. The results are applied to LIBOR market models in order to deal with the …
Spectrum selectively trains LLMs based on SNR to save resources.
Trust lies at the crux of most economic transactions, with credit markets being a notable example. Drawing on insights from the literature on coordination games and network growth, we develop a simple model to clarify how trust breaks down in financial systems. We show how the arrival of bad news about a financial agen…
We develop a multi-factor stochastic volatility Libor model with displacement, where each individual forward Libor is driven by its own square-root stochastic volatility process. The main advantage of this approach is that, maturity-wise, each square-root process can be calibrated to the corresponding cap(let)vola-stri…
Generative diffusion models gradually memorize training data, losing independent dimensions.
We study some aspects of spherical symmetric dyonic non-supersymmetric black holes in supergravity coupled to chiral and vector multiplets on Kähler-Ricci solitons. Then, we have a family of dyonic non-supersymmetric black holes deformed with respect to the flow parameter related to the Kähler-Ricci soliton…
Continuous-time interpolation of volatility surfaces preserving mixtures and arbitrage-free.
There are many award-winning pre-trained Convolutional Neural Network (CNN), which have a common phenomenon of increasing depth in convolutional layers. However, I inspect on VGG network, which is one of the famous model submitted to ILSVRC-2014, to show that slight modification in the basic architecture can enhance th…
Unified framework for learning function representations using INRs and Transformers.
L-CNNs approximate gauge actions, revealing fixed points with no lattice artifacts.
Study on reliability of latent reuse in diffusion models under distribution shift.
Improved text generation with discourse-aware soft prompts.
Training generative adversarial networks (GANs) on high quality (HQ) images involves important computing resources. This requirement represents a bottleneck for the development of applications of GANs. We propose a transfer learning technique for GANs that significantly reduces training time. Our approach consists of f…
The growing use of Machine Learning has produced significant advances in many fields. For image-based tasks, however, the use of deep learning remains challenging in small datasets. In this article, we review, evaluate and compare the current state-of-the-art techniques in training neural networks to elucidate which te…
Machine learning finds a compact fixed point action for SU(3) gauge theory.
SIREN protocol corrects optimistic winner's scores in LLM evaluation.
This paper formalises the problem of online algorithm selection in the context of Reinforcement Learning. The setup is as follows: given an episodic task and a finite number of off-policy RL algorithms, a meta-algorithm has to decide which RL algorithm is in control during the next episode so as to maximize the expecte…
Sparse random networks reduce communication in federated learning.
We define systems of pre-extremals for the energy functional of regular rheonomic Lagrange manifolds and show how they induce well-defined Hamilton orthogonal nets. Such nets have applications in the modelling of e.g. wildfire spread under time- and space-dependent conditions. The time function inherited from such a Ha…