Deep vanilla transformers trained without shortcuts achieve similar performance to standard models.
problem Training deep vanilla transformers without shortcuts and normalizations.
method Parameter initializations, bias matrices, and location-dependent rescaling.
result Deep vanilla transformers can train at similar speeds and performance to standard models.
Deep RL policies are vulnerable to adversarial perturbations, but vanilla training yields more robust policies.
problem Vulnerability of deep reinforcement learning policies to adversarial perturbations.
method Analysis of deep reinforcement learning policy landscape and comparison of vanilla vs. adversarial training.
result Vanilla training yields more robust policies compared to adversarial training.
BEMA reduces bias in EMA, leading to faster convergence and better performance.
problem Stochasticity in language model fine-tuning destabilizes training.
method Bias-Corrected Exponential Moving Average (BEMA) augmentation of EMA.
result BEMA leads to significantly improved convergence rates and final performance.
New method trains deep vanilla networks as fast as ResNets without shortcut connections.
problem Training very deep neural networks is challenging.
method Developed a new type of transformation compatible with Leaky ReLUs.
result Validation accuracies with deep vanilla networks are competitive with ResNets and significantly higher.
Free adversarial training reduces the generalization gap compared to vanilla method.
problem Improving generalization in adversarial training.
method Analysis of algorithmic stability in free adversarial training.
result Free adversarial training shows a lower generalization gap.
Vanilla SGD learns SIM from anisotropic data without explicit covariance estimation.
problem Learning SIM from anisotropic Gaussian inputs.
method Vanilla Stochastic Gradient Descent (SGD) trained on SIM with anisotropic input.
result Vanilla SGD adapts to anisotropic data's covariance structure.
We apply supervised deep neural networks (DNNs) for pricing and calibration of both vanilla and exotic options under both diffusion and pure jump processes with and without stochastic volatility. We train our neural network models under different number of layers, neurons per layer, and various different activation fun…
New metrics differentiate effective OOD sets for training calibrated CNNs.
problem Vanilla CNNs struggle with out-of-distribution (OOD) samples.
method Developed metrics based on generalization errors of Augmented-CNN.
result Most protective OOD sets lead to better A-CNN performance.
Paper examines fairness of data augmentation methods, finding vanilla Mixup outperforms Fair Mixup.
problem Improving fairness in classification models with limited minority data.
method Uses multicalibration to rigorously evaluate and improve data augmentation methods for classification fairness.
result Vanilla Mixup outperforms Fair Mixup and baseline methods in fairness and accuracy, especially with small minority groups.
CutMix enhances feature learning in neural networks, improving test accuracy.
problem Understanding and improving feature learning in neural networks using patch-level augmentation.
method Three distinct methods: vanilla training, Cutout training, and CutMix training were studied.
result CutMix training yields the highest test accuracy and learns all features and noise vectors evenly.
NS3L improves SSL algorithms by adding negative sampling, achieving better results.
problem Improving semi-supervised learning performance.
method Negative Sampling in Semi-Supervised Learning (NS3L) algorithm.
result NS3L significantly improves SSL algorithms like VAT and MixMatch.
Optimal hedging strategies for exotic options using vanilla options.
problem Hedging exotic options with illiquid vanilla options.
method Simple approximations and variational techniques in a market model and stochastic volatility model framework.
result Optimal Delta and Vega hedging strategies can be computed easily.
In recent years, state-of-the-art methods in computer vision have utilized increasingly deep convolutional neural network architectures (CNNs), with some of the most successful models employing hundreds or even thousands of layers. A variety of pathologies such as vanishing/exploding gradients make training such deep n…
Vanilla GANs are connected to Wasserstein distance for better understanding.
problem Understanding the statistical properties of Vanilla GANs.
method Connecting Vanilla GANs to Wasserstein distance and proving an oracle inequality.
result An oracle inequality for Vanilla GANs in Wasserstein distance is obtained.
This work investigates image augmentations for GAN training, improving image quality.
problem Improving the accuracy and robustness of GAN models for image synthesis.
method Systematic study of various image augmentation techniques for GAN training.
result Vanilla GANs can achieve state-of-the-art generation quality with image augmentations.
SIFT reduces training time by selecting samples with approximate losses.
problem Reducing training time by selecting samples with large approximate losses.
method Developed SIFT which uses early exiting to obtain approximate losses with intermediate layer representations for sample selection.
result SIFT achieves significant gains in training time and number of backpropagation steps without optimized implementation.
New bounds for shallow neural networks with deterministic parameters.
problem Developing generalisation bounds for shallow neural networks.
method PAC-Bayesian theory applied to shallow neural networks with deterministic parameters.
result Empirical non-vacuous bounds for shallow neural networks trained with vanilla SGD.
This paper uses basket option formulas to price vanilla options with discrete dividends.
problem Pricing vanilla options on stocks with discrete cash dividends.
method Uses existing basket option formulas for European options on a single asset with cash dividends in the piecewise lognormal model.
result Explains the use of basket option formulas for a specific problem in the piecewise lognormal model.
New method speeds up nuclear-norm constrained learning over multiple machines.
problem Synchronization slowdown and high communication costs in large-scale learning.
method Asynchronous Stochastic Frank-Wolfe (SFW-asyn) method.
result SFW-asyn achieves the same convergence rate as vanilla SFW but with speed-ups almost linear to the number of machines.
Stagewise training strategy is widely used for learning neural networks, which runs a stochastic algorithm (e.g., SGD) starting with a relatively large step size (aka learning rate) and geometrically decreasing the step size after a number of iterations. It has been observed that the stagewise SGD has much faster conve…
Study on adversarial training's impact on deep neural reinforcement learning policies.
problem Vulnerability of deep neural reinforcement learning policies to imperceptible adversarial perturbations.
method Two parallel approaches: Fourier spectrum analysis and feature sensitivity measurement.
result Adversarially trained policies are more sensitive to low frequency perturbations.
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques develo…
Fractal learning rate schedules accelerate vanilla gradient descent.
problem Difficulty in tuning learning rates in iterative optimization.
method Introduce Chebyshev learning rate schedule for gradient descent.
result Locally unstable updates can lead to convergence in deep learning.
Mixup reduces the sample complexity of finding optimal decision boundaries for more separable data.
problem Finding optimal decision boundaries in separable data distributions.
method Mixup technique applied to binary linear classification problems.
result Mixup significantly reduces the sample complexity for more separable data.
DDSME outperforms SME in estimating multimodal distributions.
problem Efficiency of score matching in multimodal distributions.
method Diffusion-based denoising score matching (DDSME) compared to vanilla score matching (SME).
result DDSME avoids the error bound deterioration of SME with increasing mode separation.
Recurrent neural networks have gained widespread use in modeling sequence data across various domains. While many successful recurrent architectures employ a notion of gating, the exact mechanism that enables such remarkable performance is not well understood. We develop a theory for signal propagation in recurrent net…
AdamL optimizes deep learning models by incorporating loss function information.
problem Adaptive optimizers can suffer from poor generalization due to nonuniform gradient scaling.
method AdamL is a novel adaptive optimizer that considers loss function information for better generalization.
result AdamL achieves faster convergence or lower objective function values compared to other optimizers.
Geometric interpretation improves VAE performance and robustness.
problem Improving Variational Autoencoder performance and robustness.
method Introducing a geometric perspective on VAEs, sampling from the Riemannian latent space.
result Improved generation and interpolations with competitive or better performance on benchmark datasets.
Vanilla Bayesian optimization performs well in high dimensions.
problem Bayesian optimization's poor performance in high-dimensional problems.
method Identified and addressed degeneracies, proposed scaling of Gaussian process lengthscale prior.
result Vanilla Bayesian optimization outperforms existing algorithms in high-dimensional tasks.
New method uses neural networks for better financial hedging.
problem Spanning multi-asset payoffs with vanilla options.
method One-hidden-layer feedforward neural networks for numerical solution.
result Better hedging results with neural networks compared to single-asset approaches.
Algorithm improves vanilla option pricing accuracy during and before COVID-19.
problem Improving vanilla option pricing accuracy during and before the pandemic.
method Combinational Mutation Strategy of Differential Evolution (CmDE) algorithm for bi-objective optimization.
result Algorithm approximates real market vanilla option prices more accurately than Black-Scholes.
TorchGAN is a PyTorch based framework for writing succinct and comprehensible code for training and evaluation of Generative Adversarial Networks. The framework's modular design allows effortless customization of the model architecture, loss functions, training paradigms, and evaluation metrics. The key features of Tor…
The Bass model is calibrated to vanilla options using a fixed-point equation.
problem Calibration of the Bass local volatility model to vanilla options.
method Solving a fixed-point equation to achieve calibration.
result Existence and uniqueness of the solution to the fixed-point equation, and linear convergence of the fixed-point iteration scheme.
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentum, Adam) for a variety of vision problems (classification, detection, segmentation). Importantly, our algorithms provide better, faster and …
Our paper introduces an efficient combination of established techniques to improve classifier performance, in terms of accuracy and training time. We achieve two-fold to ten-fold speedup in nearing state of the art accuracy, over different model architectures, by dynamically tuning the learning rate. We find it especia…
In this paper, we aim at providing an introduction to the gradient descent based optimization algorithms for learning deep neural network models. Deep learning models involving multiple nonlinear projection layers are very challenging to train. Nowadays, most of the deep learning model training still relies on the back…
New FX option interpolations impact implied volatilities.
problem Different interpolations of FX option quotes lead to varying implied volatilities.
method Analysis of various exact interpolations of broker quotes.
result Different interpolations result in different implied volatilities.
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy attacks. In this work we demonstrate how model inversion attacks, extracting trai…
Initializing the weights and the biases is a key part of the training process of a neural network. Unlike the subsequent optimization phase, however, the initialization phase has gained only limited attention in the literature. In this paper we discuss some consequences of commonly used initialization strategies for va…
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…
ARM improves multivariate time series forecasting by better capturing series-wise relationships.
problem Challenges in handling complex temporal-contextual relationships in multivariate time series forecasting.
method ARM is an enhanced multivariate LTSF architecture that employs Adaptive Univariate Effect Learning, Random Dropping, and Multi-kernel Local Smoothing.
result ARM outperforms vanilla Transformers on multiple benchmarks without significantly increasing computational costs.
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.
problem Investigates appropriate implied volatility extrapolation at extreme strikes.
method Compares Bachelier and Black-Scholes models, focusing on normal distribution and vanilla options.
result Bachelier implied variance grows at most linearly in log-moneyness, similar to Black-Scholes.
C-Mixup improves generalization in regression tasks by adjusting label similarity.
problem Improving generalization in regression tasks with limited data.
method C-Mixup adjusts the probability of mixing examples based on label similarity.
result C-Mixup achieves better generalization and robustness compared to vanilla mixup.
PAGE is a simple gradient estimator for nonconvex optimization problems.
problem Nonconvex optimization problems in machine learning.
method PAGE is a probabilistic gradient estimator that uses vanilla SGD with probability and a small adjustment with probability 1-p.
result PAGE achieves optimal convergence rates for nonconvex finite-sum and online problems.
Analyzes adversarial training's impact on loss landscape, proposing PAS to improve model performance.
problem Challenges in optimizing models under adversarial training due to loss landscape properties.
method Analytical studies of adversarial loss functions, numerical analyses, PAS strategy.
result Adversarial training impairs optimization, but PAS strategy improves model performance.
Pretraining models improves text classification accuracy, but diminishing returns are observed with large datasets.
problem Improving text classification accuracy with pretrained models.
method Examined the benefits of pretrained models on text classification tasks with varying amounts of training data.
result As the number of training examples grows into the millions, the accuracy gap between pretrained BERT-based models and vanilla LSTM narrows to within 1%.
Improved stable RNNs trained faster with less expressibility trade-off.
problem Stable recurrent neural networks are hard to train without sacrificing expressibility.
method Implicit model structure with contraction analysis for stable models.
result Significant increase in training speed and model performance.