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.
New probabilistic scheme combines deep learning with Runge-Kutta methods for solving PDEs.
A new learning scheme improves model efficiency and performance.
We establish a tight characterization of the worst-case rates for the excess risk of agnostic learning with sample compression schemes and for uniform convergence for agnostic sample compression schemes. In particular, we find that the optimal rates of convergence for size- agnostic sample compression schemes are of…
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to preserve optimality of stochastic policies, and demonstrate that the ability of an a…
Neural networks learn task-specific features, influenced by nonlinearity.
It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. Aiming at characterizing the optimal strategies, we consider learning of Gaussian Processes (GPs) in distributed systems as a pivotal example. We first ad…
We investigate Fano schemes of conditionally generic intersections, i.e. of hypersurfaces in projective space chosen generically up to additional conditions. Via a correspondence between generic properties of algebraic varieties and events in probability spaces that occur with probability one, we use the obtained resul…
Extends JKO scheme for iterative algorithms with unknown parameters.
Automates standards design through machine learning.
Reduces multiclass and regression compression schemes to binary ones.
This paper proposes a new method to learn integration schemes for complex ODEs.
We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction. The proposed scheme is a non-linear generalization of structured low rank (SLR) methods that self learn linear annihilation filters from the same subject. It pre-learns non-linear annihilation relations in the Fourie…
Neural Galerkin schemes use active learning to solve high-dimensional equations.
New sampling scheme improves ML accuracy in physics simulations.
New learning scheme solves high-dimensional semi-linear PDEs using sparse grids and Picard approximations.
Modulo-SK outperforms Deepcode in error probability and feedback rounds.
Different types of training data have led to numerous schemes for supervised classification. Current learning techniques are tailored to one specific scheme and cannot handle general ensembles of training data. This paper presents a unifying framework for supervised classification with general ensembles of training dat…
New method learns population dynamics from snapshots using JKO scheme and inverse optimization.
In this paper we consider the dictionary learning problem for sparse representation. We first show that this problem is NP-hard by polynomial time reduction of the densest cut problem. Then, using successive convex approximation strategies, we propose efficient dictionary learning schemes to solve several practical for…
Two new coding schemes improve the efficient communication of noisy data.
Study shows different initialization schemes for LoRA finetuning impact performance.
Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant represent…
Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant represent…
In this work, a non-gradient descent learning (NGDL) scheme was proposed for deep feedforward neural networks (DNN). It is known that an autoencoder can be used as the building blocks of the multi-layer perceptron (MLP) DNN, the MLP is taken as an example to illustrate the proposed scheme of pseudoinverse learning algo…
Structured low-rank (SLR) algorithms, which exploit annihilation relations between the Fourier samples of a signal resulting from different properties, is a powerful image reconstruction framework in several applications. This scheme relies on low-rank matrix completion to estimate the annihilation relations from the m…
There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and per…
Adaptive quantization improves SGD accuracy in data-parallel settings.
A new one-point feedback scheme improves ZO algorithms for black-box optimization.
Phase Modulation on the Hypersphere (PMH) is a power efficient modulation scheme for the \textit{load-modulated} multiple-input multiple-output (MIMO) transmitters with central power amplifiers (CPA). However, it is difficult to obtain the precise channel state information (CSI), and the traditional optimal maximum lik…
The paper analyzes convergence of Riemannian SA schemes for stochastic optimization.
We consider the problem of dictionary learning under the assumption that the observed signals can be represented as sparse linear combinations of the columns of a single large dictionary matrix. In particular, we analyze the minimax risk of the dictionary learning problem which governs the mean squared error (MSE) perf…
Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networ…
This paper develops coding techniques to reduce the running time of distributed learning tasks. It characterizes the fundamental tradeoff to compute gradients (and more generally vector summations) in terms of three parameters: computation load, straggler tolerance and communication cost. It further gives an explicit c…
Resource allocation improved using machine learning from terminal positions.
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to…
ISALT uses inference to simulate SDEs with large time-steps, improving efficiency.
Power system emergency control is generally regarded as the last safety net for grid security and resiliency. Existing emergency control schemes are usually designed off-line based on either the conceived "worst" case scenario or a few typical operation scenarios. These schemes are facing significant adaptiveness and r…
Paper explores weighted averaging schemes for SGD, achieving asymptotic normality and optimality.
New aggregation methods improve robustness and efficiency in distributed learning.
Deep learning accelerates Monte Carlo SDE simulations with large time steps.
Develops a numerical scheme for solving path-dependent FBSDEs and PDEs.
A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforwa…
A new unsupervised learning method calibrates rough volatility models efficiently.
Human inertial thinking schemes can be formed through learning, which are then applied to quickly solve similar problems later. However, when problems are significantly different, inertial thinking generally presents the solutions that are definitely imperfect. In such cases, people will apply creative thinking, such a…
This paper proposes a novel scheme for the watermarking of Deep Reinforcement Learning (DRL) policies. This scheme provides a mechanism for the integration of a unique identifier within the policy in the form of its response to a designated sequence of state transitions, while incurring minimal impact on the nominal pe…
GPU speeds up Monte Carlo simulations for large time steps.
Paper proves global optimality of a simple optimization scheme for learning DAG models.
In this paper, we present a Bayesian view on model-based reinforcement learning. We use expert knowledge to impose structure on the transition model and present an efficient learning scheme based on variational inference. This scheme is applied to a heteroskedastic and bimodal benchmark problem on which we compare our …