arXiv research

Controller-Augmented Hidden Markov Models (CHMMs) are a framework for constrained sequential inference.

RAD enhances RL algorithms with data augmentations.

ODVICE augments EHR cohorts using ontology to improve analysis robustness.

For training the sequence-to-sequence voice conversion model, we need to handle an issue of insufficient data about the number of speech pairs which consist of the same utterance. This study experimentally investigated the effects of Mel-spectrogram augmentation on training the sequence-to-sequence voice conversion (VC…

In this article, associated to a (bordered) Legendrian graph, we study and show the equivalence between two categorical Legendrian isotopy invariants: the augmentation category, a unital $A_{\infty}$-category, which lifts the set of augmentations of the associated Chekanov-Eliashberg DGA, and a DG category of construct…

Expert augmentation improves hybrid model generalization.

The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for th…

A new meta-algorithm for estimating the conditional average treatment effects is proposed in the paper. The main idea underlying the algorithm is to consider a new dataset consisting of feature vectors produced by means of concatenation of examples from control and treatment groups, which are close to each other. Outco…

Machine-assisted treatment recommendations hold a promise to reduce physician time and decision errors. We formulate the task as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications. It is built on the …

Curriculum learning and imitation learning improve control over financial time-series data.

CoDA augments data with counterfactuals from local causal structures.

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reducti…

Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern…

A new framework reduces traffic congestion by 36%.

Bayesian classification improves with explicit aleatoric uncertainty.

Cross-regularization adapts model complexity during training.

Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances ar…

Entangled bisimulation improves policy learning from visual input.

State-augmented algorithm optimizes wireless network resource management.

New method solves constrained optimization problems efficiently.

Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial agent across categories of functionality, with the goal of faster development o…

Simple image augmentation boosts deep RL from pixels.

Synthetic augmentation improves financial machine learning performance in variance-dominant regimes.

Improved reinforcement learning with deep learning.

Financial Wind Tunnel generates versatile market data for model testing.

SC-InfoNCE improves InfoNCE for feature clustering in contrastive learning.

We present a novel technique to solve the problem of managing optimally a pumped hydroelectric storage system. This technique relies on representing the system as a stochastic optimal control problem with state constraints, these latter corresponding to the finite volume of the reservoirs. Following the recent level-se…

Study adapts AI research methods to analyze image augmentation impacts on neural network operations.

A new method tackles nonconvex optimization with penalties and proximal terms.

Optimistic RL algorithms are simplified for deep RL with competitive performance.

New framework explains data augmentation's role in machine learning.

The paper provides theoretical guarantees for behavior cloning using generative models.

ToolChain-CRC addresses the risk-control problem for retrieval-augmented and tool-using agents under drift.

SBA improves neural network generalization by dynamically augmenting data.

Paper develops heavy-tailed embeddings for better text classification and augmentation.

Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each…

Generative AI improves stock selection by synthesizing features from diverse data sources.

New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.

New method learns dynamics from sparse data using geometric constraints.

Paper proposes a sparse synthetic control method to select important predictors.

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…

New unsupervised learning task improves RL performance.

CODA resolves coordination issues in offline multi-agent reinforcement learning.

We address the problem of reverse engineering of stripped executables, which contain no debug information. This is a challenging problem because of the low amount of syntactic information available in stripped executables, and the diverse assembly code patterns arising from compiler optimizations. We present a novel ap…

This paper improves generative models by using data scaling and theoretical analysis.

CADD improves generative quality by augmenting discrete diffusion with continuous latent space.

Framework for estimating treatment effects using external control data.

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's state space enabling it to scale up to a more complex problems but also increases t…