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.
Nonparametric adaptive robust control tackles model uncertainty in stochastic processes.
Paper proposes SRA algorithm for online learning robustness and adaptivity.
In this paper we propose a new methodology for solving an uncertain stochastic Markovian control problem in discrete time. We call the proposed methodology the adaptive robust control. We demonstrate that the uncertain control problem under consideration can be solved in terms of associated adaptive robust Bellman equa…
We develop the method of stochastic modified equations (SME), in which stochastic gradient algorithms are approximated in the weak sense by continuous-time stochastic differential equations. We exploit the continuous formulation together with optimal control theory to derive novel adaptive hyper-parameter adjustment po…
New model for display advertising with stochastic and adversarial components.
Improved linear regression with privacy and robustness guarantees.
New metric derived for robust optimization in stochastic control problems.
Study time-inconsistent control problems with model uncertainty, solving portfolio selection.
Optimal asset allocation strategy outperforms stochastic benchmark.
Unified framework for adaptive connection sampling in GNNs improves performance and robustness.
Paper tackles SMPC for linear systems with unknown noise distribution.
The paper tackles robust control with uncertain dependence using data-driven methods.
Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on stationary problems, and permitting learning rates to grow appropriately in non-stati…
New robust control method for uncertain systems using bootstrapped noise.
We propose an adaptive optimization method for deep learning that dynamically adjusts batch size.
We provide a numerically robust and fast method capable of exploiting the local geometry when solving large-scale stochastic optimisation problems. Our key innovation is an auxiliary variable construction coupled with an inverse Hessian approximation computed using a receding history of iterates and gradients. It is th…
In this paper, we present GASG21 (Grassmannian Adaptive Stochastic Gradient for norm minimization), an adaptive stochastic gradient algorithm to robustly recover the low-rank subspace from a large matrix. In the presence of column outliers, we reformulate the batch mode matrix norm minimization with…
Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the noise in stochastic estimates of the gradients. In this paper, we propose a new ad…
We prove that the norm version of the adaptive stochastic gradient method (AdaGrad-Norm) achieves a linear convergence rate for a subset of either strongly convex functions or non-convex functions that satisfy the Polyak Lojasiewicz (PL) inequality. The paper introduces the notion of Restricted Uniform Inequality of Gr…
Paper analyzes adaptive Lasso for high-dimensional diffusion processes, improving support recovery and bias.
Estimates outcomes under hypothetical scenarios using a flexible framework.
Study robust control for systems with continuous states using adversarial perturbations.
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with mom…
High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is to automate a part of tuning process. Aiming at a fast, robust, and widely-appli…
This paper improves offline contextual bandits using distributional robustness.
New algorithms achieve optimal robustness in stochastic convex optimization under contamination.
The challenge in controlling stochastic systems in which low-probability events can set the system on catastrophic trajectories is to develop a robust ability to respond to such events without significantly compromising the optimality of the baseline control policy. This paper presents CelluDose, a stochastic simulatio…
First robust bandit algorithm for contextual bandits with sub-linear regret.
SALSA automatically adjusts learning rates in stochastic gradient methods.
Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this pap…
We develop model-based methods for solving stochastic convex optimization problems, introducing the approximate-proximal point, or aProx, family, which includes stochastic subgradient, proximal point, and bundle methods. When the modeling approaches we propose are appropriately accurate, the methods enjoy stronger conv…
WALNUTS improves sampling efficiency and robustness for multi-scale distributions.
ARFF reduces spectral bias in SGD-trained neural networks.
This paper proposes SplitSGD, a new dynamic learning rate schedule for stochastic optimization. This method decreases the learning rate for better adaptation to the local geometry of the objective function whenever a stationary phase is detected, that is, the iterates are likely to bounce at around a vicinity of a loca…
Adaptive learning of SPDE solutions using score-based diffusion models.
Bayesian approach for policy search in stochastic domains.
We introduce algorithms for online, full-information prediction that are competitive with contextual tree experts of unknown complexity, in both probabilistic and adversarial settings. We show that by incorporating a probabilistic framework of structural risk minimization into existing adaptive algorithms, we can robus…
Despite the development of numerous adaptive optimizers, tuning the learning rate of stochastic gradient methods remains a major roadblock to obtaining good practical performance in machine learning. Rather than changing the learning rate at each iteration, we propose an approach that automates the most common hand-tun…
A new deep hedging framework improves efficiency and robustness.
A new method for machine learning updates reduces complexity and improves robustness.
New measure assesses neural network models' functional similarity.
SGLBO optimizes quantum circuits with fewer measurements, improving accuracy and noise resilience.
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative studies of automatic and human speech recognition that associate standard non-adaptiv…
Online minimization of an unknown convex function over the interval is considered under first-order stochastic bandit feedback, which returns a random realization of the gradient of the function at each query point. Without knowing the distribution of the random gradients, a learning algorithm sequentially choo…
New method tackles model uncertainty in stochastic control using Bayesian nonparametrics.
An online learning framework for survival analysis with real-time adaptation.
A new method for robust product Markovian quantization overcomes numerical instabilities.
During recent years there has been an increased interest in stochastic adaptations of limited memory quasi-Newton methods, which compared to pure gradient-based routines can improve the convergence by incorporating second order information. In this work we propose a direct least-squares approach conceptually similar to…