We consider the problem of learning a manifold from a teacher's demonstration. Extending existing approaches of learning from randomly sampled data points, we consider contexts where data may be chosen by a teacher. We analyze learning from teachers who can provide structured data such as individual examples (isolated …
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Demonstration data”
Improves online learning with expert demonstrations, quality matters.
problem Improving online learning through offline demonstration data.
method Thompson sampling applied to a multi-armed bandit model, informed by expert demonstrations and Bayes' rule.
result Substantial empirical regret reduction with expert demonstrations, improving online performance.
Robust real-world learning should benefit from both demonstrations and interactions with the environment. Current approaches to learning from demonstration and reward perform supervised learning on expert demonstration data and use reinforcement learning to further improve performance based on the reward received from …
New RL method handles diverse human operator data.
problem Handling data from multiple, unknown policies.
method Domain-Invariant Model-based Offline RL (DIMORL) with Risk Extrapolation (REx).
result Models trained with REx generalize better across different demonstrators.
DPBD simplifies labeling functions through interactive demonstrations.
problem Difficulty in writing labeling functions for large-scale labeled training data.
method Data Programming by Demonstration (DPBD) framework using interactive demonstrations.
result Ruler system generates labeling rules more easily and with higher user satisfaction.
Identifies latent actions and dynamics from offline data with diverse demonstrators.
problem Recovering latent actions and environment dynamics from action-free trajectories.
method Assumes distinct policies for each demonstrator, identifies latent transitions and policies via matrix factorization.
result Identifies latent transitions and demonstrator policies up to permutation.
We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as learning a proposal distribution generator for approximate inference in the synthetic-d…
Bayesian Experience Reuse improves learning from multiple experts.
problem Learning from multiple experts with conflicting goals.
method Bayesian neural networks with shared features to model uncertainty and derive a probability distribution over expert models.
result BERS method effectively samples demonstrations from the derived distribution to reuse them in new tasks.
Action chunking and data exploration improve behavior cloning in robotics.
problem Exponential errors in learning from demonstrations for continuous control tasks.
method Action chunking and exploratory data collection.
result Control-theoretic stability is key to improving imitation learning.
Data describing historical economic growth are analysed. They demonstrate convincingly that the takeoffs from stagnation to growth, claimed in the Unified Growth Theory, never happened. This theory is again contradicted by data, which were used, but never properly analysed, during its formulation. The absence of the cl…
Novel framework learns policies from noisy expert demonstrations.
problem Learning effective policies with noisy expert demonstrations.
method Adaptive learning framework that jointly interacts with the environment and expert demonstrations, assigning weights to filter out noisy demonstrations.
result The proposed approach learns robustly with noisy demonstrations and achieves higher performance in fewer iterations.
This paper reports applications of Difference of Convex functions (DC) programming to Learning from Demonstrations (LfD) and Reinforcement Learning (RL) with expert data. This is made possible because the norm of the Optimal Bellman Residual (OBR), which is at the heart of many RL and LfD algorithms, is DC. Improvement…
Role-wise data augmentation improves knowledge distillation effectiveness.
problem Existing knowledge distillation methods fail to utilize the full potential of teacher-student data interaction.
method Design and implement data augmentation agents with distinct roles for teacher and student.
result Specially tailored data points enhance the demonstration of teacher's knowledge to the student.
A comprehensive methodology is provided for smoothing noisy, irregularly sampled data with non-Gaussian noise using smoothing splines. We demonstrate how the spline order and tension parameter can be chosen a priori from physical reasoning. We also show how to allow for non-Gaussian noise and outliers which are typical…
Data stream classification methods demonstrate promising performance on a single data stream by exploring the cohesion in the data stream. However, multiple data streams that involve several correlated data streams are common in many practical scenarios, which can be viewed as multi-task data streams. Instead of handli…
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a comp…
We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories. This issue of missing trajectory data or information occurs in many situations, e.g., GPS signals from vehicl…
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for many learning problems including time series modelling, spatial data, and images. The model embeds …
ORIL learns a reward function from unlabeled data to improve robot learning.
problem Leveraging unlabeled data for robot learning.
method ORIL learns a reward function from demonstrator and unlabeled trajectories, annotates data, and trains an agent via offline reinforcement learning.
result ORIL consistently outperforms BC agents on various robotic tasks.
The main contribution of this paper is the development of a new decision tree algorithm. The proposed approach allows users to guide the algorithm through the data partitioning process. We believe this feature has many applications but in this paper we demonstrate how to utilize this algorithm to analyse data sets cont…
This study tackles offline RL with perturbed data sources, deriving a lower bound and proposing an optimal algorithm.
problem Understanding offline RL with multiple perturbed data sources.
method Derives an information-theoretic lower bound, proposes HetPEVI algorithm considering sample and source uncertainties.
result HetPEVI is optimal up to a polynomial factor of the horizon length and can solve offline RL tasks.
This research shows how to learn shared representations from unpaired data.
problem Learning shared representations from unpaired data.
method Spectral embeddings of random walk matrices from each unimodal representation.
result Shared representations can be learned almost exclusively from unpaired data.
We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects. This problem presents a number of major challenges. Video demonstrations without teleoperation are easy for humans to…
Reduces data leakage in distributed deep learning models.
problem Prevents reconstruction of sensitive raw data patterns during client communications.
method Reduces distance correlation between raw data and learned representations.
result Resilient to reconstruction attacks while maintaining model accuracy.
Reinforcement learning approaches have long appealed to the data management community due to their ability to learn to control dynamic behavior from raw system performance. Recent successes in combining deep neural networks with reinforcement learning have sparked significant new interest in this domain. However, pract…
Machine learning algorithms can misrepresent training data, study finds.
problem Misrepresentation of training data in machine learning algorithms.
method Demonstrated through underestimation of training data due to irreducible error, regularization, and class imbalance.
result Careful management of synthetic counterfactuals can mitigate underestimation bias.
Citizen science projects are successful at gathering rich datasets for various applications. However, the data collected by citizen scientists are often biased --- in particular, aligned more with the citizens' preferences than with scientific objectives. We propose the Shift Compensation Network (SCN), an end-to-end l…
AWAC combines offline and online data to accelerate RL learning.
problem Challenges in applying RL to real-world robotic control due to exploration and sample complexity.
method Combines sample-efficient dynamic programming with maximum likelihood policy updates.
result AWAC enables rapid learning of robotic skills with prior data and online experience.
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images is data inefficient. The agent must learn feature representation of complex stat…
Paper tackles transfer RL under unobserved context, developing methods to reduce bias.
problem Transfer RL with unobserved contextual information leading to biased models.
method Develops causal bounds on transition and reward functions using demonstrator's data.
result Proposes Q learning and UCB-Q learning algorithms that converge to true value function without bias.
Study linear contextual bandits with confounded offline data, improving regret bounds.
problem Linear contextual bandits with confounded offline data.
method Construct a linear bandit algorithm that utilizes projected information.
result Proved regret bounds that improve current bounds by a factor related to visible dimensionality.
We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able to learn from training data of this type are potentially of great use as many real-world datasets ar…
Sparse principal component analysis (SPCA) has emerged as a powerful technique for modern data analysis, providing improved interpretation of low-rank structures by identifying localized spatial structures in the data and disambiguating between distinct time scales. We demonstrate a robust and scalable SPCA algorithm b…
New model learns better policies from expert demonstrations with higher efficiency.
problem Learning accurate policies from expert demonstrations with high efficiency.
method Generative adversarial imitation learning (GAIL) model that learns -divergence automatically.
result Learns better policies with higher data efficiency in physics-based control tasks.
In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional Autoencoders have proven to structure data naturally they fail to discover sema…
Over the years, several studies have demonstrated that there exist significant disparities in health indicators in the United States population across various groups. Healthcare expense is used as a proxy for health in algorithms that drive healthcare systems and this exacerbates the existing bias. In this work, we foc…
New assumptions help identify causal relationships in data.
problem Challenges in identifying causal relationships from observational data.
method Introduced typed directed acyclic graphs to constrain causal relationships.
result The proposed assumptions lead to significant gains in causal graph identification.
CupNet prunes neural nets for cup-shaped data.
problem Pruning neural networks for cup-shaped data.
method Used simulated cup drawing data to prune a neural network.
result Pruning effectively reduces network size for cup-shaped data.
We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient fea…
Mixes higher-order simplicial complexes for data augmentation.
problem Lack of labeled data for complex systems with multiway interactions.
method Proposes mixup mechanisms for simplicial complexes, including linear and nonlinear mixup, and a convex clustering mixup.
result Synthetic simplicial complexes interpolate between existing data based on homomorphism densities.
Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert demonstration in practice. In this work, we propose Active Reinforcement Learning wit…
NICE model estimates causal effects for image treatments.
problem Challenges in causal effect estimation for multi-dimensional treatments.
method Proposes NICE model for image treatments, incorporating rich multidimensional information.
result NICE significantly outperforms existing models in estimating causal effects for image treatments.
Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with…
One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Videocs.LG
Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of demonstrations in varyi…
The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts and amateurs. IL in such situations can be challenging, especially when the lev…
Normalizing flows improve density estimation from noisy data.
problem Estimating underlying density from noisy samples.
method Use normalizing flows for density estimation with arbitrary noise distributions, using amortized variational inference.
result Normalizing flows can outperform Gaussian mixtures for density deconvolution.
Improved anomaly detection in time series data using kervolutional neural networks.
problem Anomaly detection in time series data.
method Mixed kervolutional and convolutional layers in a temporal auto-encoder.
result The mixed model detects anomalies more sensitively in time series data.