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.
The paper explores how regularization can improve multi-objective learning with high-dimensional data.
This work investigates image augmentations for GAN training, improving image quality.
It is well known that any sufficiently regular one-dimensional payoff function has an explicit static hedge by bonds, forward contracts and lots of vanilla options. We show that the natural extension of the corresponding representation leads to a static hedge based on the same instruments along with traffic light optio…
A main theoretical interest in biology and physics is to identify the nonlinear dynamical system (DS) that generated observed time series. Recurrent Neural Networks (RNNs) are, in principle, powerful enough to approximate any underlying DS, but in their vanilla form suffer from the exploding vs. vanishing gradients pro…
Study optimizes option pricing with robust strategies, ensuring consistency with vanilla option prices.
New L2 regularization improves softmax MAB performance.
Noise injection before gradient steps helps in regularization for neural networks.
New algorithm improves convergence of gradient boosting trees.
Optimal hedging strategies for exotic options using vanilla options.
This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network. The prediction errors for the model are included in the basic DQN loss as additional regularizers. This augmente…
Vanilla GANs are connected to Wasserstein distance for better understanding.
In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compared to regular full RNNs in most of our experiments. We show the benefits of using diagonal recurrent…
In this paper, we implement a stochastic deflator with five economic and financial risk factors: interest rates, market price of risk, stock prices, default intensities, and convenience yields. We examine the deflator with different financial assets, such as stocks, zero-coupon bonds, vanilla options, and corporate cou…
This paper uses basket option formulas to price vanilla options with discrete dividends.
DDSME outperforms SME in estimating multimodal distributions.
Neural networks learn the support of the target function through SGD's implicit regularization effect.
The main goal of this work is equipping convex and nonconvex problems with Barzilai-Borwein (BB) step size. With the adaptivity of BB step sizes granted, they can fail when the objective function is not strongly convex. To overcome this challenge, the key idea here is to bridge (non)convex problems and strongly convex …
Improves GAN-based semi-supervised learning with consistency regularization.
Deep vanilla transformers trained without shortcuts achieve similar performance to standard models.
Stochastic dual coordinate ascent (SDCA) is an effective technique for solving regularized loss minimization problems in machine learning. This paper considers an extension of SDCA under the mini-batch setting that is often used in practice. Our main contribution is to introduce an accelerated mini-batch version of SDC…
Vanilla Bayesian optimization performs well in high dimensions.
New algorithm improves CRF inference and learning.
Weighted Monte Carlo prices exotic options calibrating the probabilities of previously generated paths by a regular Monte Carlo to fit a set of option premiums. When only vanilla call and put options and forward prices are considered, the Martingale condition might not be preserved. This paper shows that this is indeed…
New method uses neural networks for better financial hedging.
New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.
Vanilla SGD learns SIM from anisotropic data without explicit covariance estimation.
We consider the problem of demixing a sequence of source signals from the sum of noisy bilinear measurements. It is a generalized mathematical model for blind demixing with blind deconvolution, which is prevalent across the areas of dictionary learning, image processing, and communications. However, state-of- the-art c…
SAIL-RevKL improves SAIL's convergence by regularizing the objective function.
New bounds on IDS for RL show how to balance computation and learning efficiency.
Algorithm improves vanilla option pricing accuracy during and before COVID-19.
The analysis of nonconvex matrix completion has recently attracted much attention in the community of machine learning thanks to its computational convenience. Existing analysis on this problem, however, usually relies on projection or regularization that involves unknown model parameters, although th…
Gradient descent recovers principal components of overparametrized asymmetric matrices without explicit regularization.
This work explores Target Networks and Functional Regularization in deep Reinforcement Learning.
Method interpolates option prices and volatilities without arbitrage.
The Bass model is calibrated to vanilla options using a fixed-point equation.
New geometric regularizers improve deep learning generalization.
We consider the discretized version of a (continuous-time) two-factor model introduced by Benth and coauthors for the electricity markets. For this model, the underlying is the exponent of a sum of independent random variables. We provide and test an algorithm, which is based on the celebrated Foellmer-Schweizer decomp…
New FX option interpolations impact implied volatilities.
XGBoost is often presented as the algorithm that wins every ML competition. Surprisingly, this is true even though predictions are piecewise constant. This might be justified in high dimensional input spaces, but when the number of features is low, a piecewise linear model is likely to perform better. XGBoost was exten…
For regular particle filter algorithm or Sequential Monte Carlo (SMC) methods, the initial weights are traditionally dependent on the proposed distribution, the posterior distribution at the current timestamp in the sampled sequence, and the target is the posterior distribution of the previous timestamp. This is techni…
Generative Adversarial Networks are known for their high quality outputs and versatility. However, they also suffer the mode collapse in their output data distribution. There have been many efforts to revamp GANs model and reduce mode collapse. This paper focuses on two of these models, PacGAN and VEEGAN. This paper ex…
We introduce a local volatility model for the valuation of options on commodity futures by using European vanilla option prices. The corresponding calibration problem is addressed within an online framework, allowing the use of multiple price surfaces. Since uncertainty in the observation of the underlying future price…
RAD improves robustness to domain annotation noise without explicit domain annotations.
Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often require proper regularization (e.g. trimming, regularized cost, projection) in order…
Cumulative entropy regularization introduces a regulatory signal to the reinforcement learning (RL) problem that encourages policies with high-entropy actions, which is equivalent to enforcing small deviations from a uniform reference marginal policy. This has been shown to improve exploration and robustness, and it ta…
In this paper, we argue that, once the costs of maintaining the hedging portfolio are properly taken into account, semi-static portfolios should more properly be thought of as separate classes of derivatives, with non-trivial, model-dependent payoff structures. We derive new integral representations for payoffs of exot…
This paper examines Bachelier implied volatility at extreme strikes.
SNN architecture shows gradient descent converges to regularized solution in matrix sensing problems.