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.
FDS tackles long horizon hyperparameter optimization issues.
DGPs with variational inference suffer from SNR issues that degrade gradient estimates, leading to unreliable training.
The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.
The computational and storage complexity of kernel machines presents the primary barrier to their scaling to large, modern, datasets. A common way to tackle the scalability issue is to use the conjugate gradient algorithm, which relieves the constraints on both storage (the kernel matrix need not be stored) and computa…
When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including …
DAIS improves AIS by resampling, avoiding gradient issues.
Adam is shown not being able to converge to the optimal solution in certain cases. Researchers recently propose several algorithms to avoid the issue of non-convergence of Adam, but their efficiency turns out to be unsatisfactory in practice. In this paper, we provide new insight into the non-convergence issue of Adam …
Generative Adversarial Networks (GAN) have shown promising results on a wide variety of complex tasks. Recent experiments show adversarial training provides useful gradients to the generator that helps attain better performance. In this paper, we intend to theoretically analyze whether supervised learning with adversar…
Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization. Our experiments in model-based reinforcement learning imply that the problem is not just a numerical issue, but it may …
EAGC boosts GCD by regulating gradient entanglement, improving known and novel category separability.
Paper tackles hyper-gradient estimation in decentralized FL over time-varying networks.
A new GAN model -GAN with tunable loss function addresses gradient vanishing and mode collapse issues.
In the first part of the paper we derive integral curvature estimates for complete gradient shrinking Ricci solitons. Our results and the recent work of Lopez-Rio imply rigidity of gradient shrinking Ricci solitons with harmonic Weyl tensor. In the second part of the paper we address the issue of existence of harmonic …
A new approach improves numerical tabular data imputation by addressing diffusion models' limitations.
Blind Descent avoids gradient issues, using a different learning approach.
Stable ResNet stabilizes gradients in deep networks.
Proposes r2SGLD for efficient constrained exploration in non-convex learning.
This work investigates how gradient-based learning performs with structured data, revealing issues and improvements.
Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to th…
Proposes a new adaptive gradient method based on gradient differences.
Sign-based algorithms (e.g. signSGD) have been proposed as a biased gradient compression technique to alleviate the communication bottleneck in training large neural networks across multiple workers. We show simple convex counter-examples where signSGD does not converge to the optimum. Further, even when it does conver…
The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum. We mainly use gradient ascent, because it is theoretically well researched. The …
Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.
Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared past gradients. In many applications, e.g. learning with large …
The choice of activation function can significantly influence the performance of neural networks. The lack of guiding principles for the selection of activation function is lamentable. We try to address this issue by introducing our variational neural networks, where the activation function is represented as a linear c…
A new algorithm reduces communication in deep learning training.
Cosine similarity can force points to grow in magnitude, causing convergence issues.
Paper introduces a new gradient statistic to improve deep learning convergence.
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on policy gradient estimation, which leads to poor sample efficiency during training. In this work, we propose a control variate method to effe…
Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical evidence suggests these two seemingly disparate issues are actually connected. In part…
New GAN formulation addresses mode collapse issue.
Forward gradients improve neural network training without backpropagation issues.
This paper tackles variance issues in GNN training by proposing a method to reduce both embedding and gradient variances.
Enhances neural architecture search efficiency and prevents performance collapse.
New method shows how order of gradient updates impacts stability and convergence in deep learning.
We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way of sharing information bet…
Proposes m-POT to improve m-OT's misspecified mappings issue.
Short note on soft-max and policy gradients in bandit problems using Lyapunov functions.
Stochastic gradient descent updates parameters with summation gradient computed from a random data batch. This summation will lead to unbalanced training process if the data we obtained is unbalanced. To address this issue, this paper takes the error variance and error mean both into consideration. The adaptively adjus…
Recent advances in stochastic gradient techniques have made it possible to estimate posterior distributions from large datasets via Markov Chain Monte Carlo (MCMC). However, when the target posterior is multimodal, mixing performance is often poor. This results in inadequate exploration of the posterior distribution. A…
Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolution strategies) help mitigate these issues, poor initialization and local optima are still concerns …
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (…
Online method learns sparse models efficiently in large scale settings.
New findings on optimal transport gradient for generative models, addressing numerical instabilities.
A new method reduces variance in training early-stage rankers for large-scale search systems.
FSGLD improves federated data sampling by correcting noisy gradients.
Most stochastic optimization methods use gradients once before discarding them. While variance reduction methods have shown that reusing past gradients can be beneficial when there is a finite number of datapoints, they do not easily extend to the online setting. One issue is the staleness due to using past gradients. …
Scout-Nd optimizes parameters of stochastic simulators efficiently.