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.
Deep networks can approximate functions with fewer learnable parameters than previously thought.
Develops methods to measure and set function-space learning rates in neural networks.
Paper introduces a new robust loss function for RL.
Supervised learning is an active research area, with numerous applications in diverse fields such as data analytics, computer vision, speech and audio processing, and image understanding. In most cases, the loss functions used in machine learning assume symmetric noise models, and seek to estimate the unknown function …
One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key strategies in scaling up reinforcement learning algorithms. In this setting, we hav…
A new model approximates complex functions in parameter space.
Develops methods for estimating constrained function-valued parameters in infinite-dimensional models.
New method improves neural network robustness by identifying functions rather than parameters.
A new method for learning function parameters in operators using data-adaptive RKHS.
Function-space MAP estimation leads to better generalization and robustness.
In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions from an interval adjusted to the target function, then randomly rotates the act…
PBVFs generalize across policies using learned value functions.
Training-free model learns SDE dynamics without training, accelerating parameter studies.
Bayesian approach uses Gaussian process for reinforcement learning.
New approach uses negative controls to estimate causal parameters without completeness conditions.
We introduce a new parameter to measure the inhomogeneity of training datasets.
Library learns Bayesian networks from mixed data without discretization.
When applying Machine Learning techniques to problems, one must select model parameters to ensure that the system converges but also does not become stuck at the objective function's local minimum. Tuning these parameters becomes a non-trivial task for large models and it is not always apparent if the user has found th…
To optimize a neural network one often thinks of optimizing its parameters, but it is ultimately a matter of optimizing the function that maps inputs to outputs. Since a change in the parameters might serve as a poor proxy for the change in the function, it is of some concern that primacy is given to parameters but tha…
This work tackles the challenge of Bayesian deep learning by proposing a new framework for matching Gaussian process priors with neural network parameters.
Proposes a RL method using simulators for stabilizing uncertain systems.
Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is propos…
Unified framework for automatic debiased machine learning for various statistical parameters.
MARS meta-learns function scores for improved predictive accuracy and uncertainty.
Gating is a key feature in modern neural networks including LSTMs, GRUs and sparsely-gated deep neural networks. The backbone of such gated networks is a mixture-of-experts layer, where several experts make regression decisions and gating controls how to weigh the decisions in an input-dependent manner. Despite having …
New method learns binary decision trees efficiently.
New learning algorithm for real analytic functions without gradient descent.
Proposes a new method for continual learning in neural networks.
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits,…
New method for unbinned, profiled unfolding in particle physics.
Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to determine a method for learning an activation function that is at the same time theoretically simple and easy to implement. Moreover, most of…
We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We first consider this problem under a certain scaling of the approximating function, leading to a regime called lazy tr…
New loss function connects learning rate and momentum.
The most widely used technology to identify the proteins present in a complex biological sample is tandem mass spectrometry, which quickly produces a large collection of spectra representative of the peptides (i.e., protein subsequences) present in the original sample. In this work, we greatly expand the parameter lear…
Deep networks learn sparse hierarchical features without CoD.
New NPG variants ensure parameter convergence in multi-agent learning.
Efficient estimators for smooth Hilbert-valued parameters with theoretical guarantees.
A successful approach to structured learning is to write the learning objective as a joint function of linear parameters and inference messages, and iterate between updates to each. This paper observes that if the inference problem is "smoothed" through the addition of entropy terms, for fixed messages, the learning ob…
Randomized methods of neural network learning suffer from a problem with the generation of random parameters as they are difficult to set optimally to obtain a good projection space. The standard method draws the parameters from a fixed interval which is independent of the data scope and activation function type. This …
We provide adaptive inference methods, based on regularization, for regular (semi-parametric) and non-regular (nonparametric) linear functionals of the conditional expectation function. Examples of regular functionals include average treatment effects, policy effects, and derivatives. Examples of non-regular f…
New insights into the top-K sparse softmax gating function for deep learning.
We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of predicted results when known data is represented as expansions in terms of various stochastic functions. The algorithm predicts the classif…
In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating an artificial intelligence system, we must make two decisions: …
This paper provides estimation and inference methods for the best linear predictor (approximation) of a structural function, such as conditional average structural and treatment effects, and structural derivatives, based on modern machine learning (ML) tools. We represent this structural function as a conditional expec…
A new meta-learning method using shared variational inference.
This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed as a cost function minimization problem). To achieve that, we compose the local feature aggregation…
DML addresses biases in machine learning by estimating nuisance functions.
New algorithm trains deep neural networks without global optimization.