Latent Properties of Lifelong Learning Systems
- URL: http://arxiv.org/abs/2207.14378v1
- Date: Thu, 28 Jul 2022 20:58:13 GMT
- Title: Latent Properties of Lifelong Learning Systems
- Authors: Corban Rivera, Chace Ashcraft, Alexander New, James Schmidt, Gautam
Vallabha
- Abstract summary: We introduce an algorithm-agnostic explainable surrogate-modeling approach to estimate latent properties of lifelong learning algorithms.
We validate the approach for estimating these properties via experiments on synthetic data.
- Score: 59.50307752165016
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Creating artificial intelligence (AI) systems capable of demonstrating
lifelong learning is a fundamental challenge, and many approaches and metrics
have been proposed to analyze algorithmic properties. However, for existing
lifelong learning metrics, algorithmic contributions are confounded by task and
scenario structure. To mitigate this issue, we introduce an algorithm-agnostic
explainable surrogate-modeling approach to estimate latent properties of
lifelong learning algorithms. We validate the approach for estimating these
properties via experiments on synthetic data. To validate the structure of the
surrogate model, we analyze real performance data from a collection of popular
lifelong learning approaches and baselines adapted for lifelong classification
and lifelong reinforcement learning.
Related papers
- Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data.
A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time.
Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
arXiv Detail & Related papers (2024-10-09T11:37:09Z) - Understanding active learning of molecular docking and its applications [0.6554326244334868]
We investigate how active learning methodologies effectively predict docking scores using only 2D structures.
Our findings suggest that surrogate models tend to memorize structural patterns prevalent in high docking scored compounds.
Our comprehensive analysis underscores the reliability and potential applicability of active learning methodologies in virtual screening campaigns.
arXiv Detail & Related papers (2024-06-14T05:43:42Z) - Runtime Verification of Learning Properties for Reinforcement Learning
Algorithms [0.0]
Reinforcement learning (RL) algorithms interact with their environment in a trial-and-error fashion.
This work develops new runtime verification techniques to predict when the learning phase has not met or will not meet qualitative and timely expectations.
arXiv Detail & Related papers (2023-11-16T11:34:37Z) - Learning Objective-Specific Active Learning Strategies with Attentive
Neural Processes [72.75421975804132]
Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting.
We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem.
Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
arXiv Detail & Related papers (2023-09-11T14:16:37Z) - Learning ECG signal features without backpropagation [0.0]
We propose a novel method to generate representations for time series-type data.
This method relies on ideas from theoretical physics to construct a compact representation in a data-driven way.
We demonstrate the effectiveness of our approach on the task of ECG signal classification, achieving state-of-the-art performance.
arXiv Detail & Related papers (2023-07-04T21:35:49Z) - Latent Variable Representation for Reinforcement Learning [131.03944557979725]
It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning.
We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle.
In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
arXiv Detail & Related papers (2022-12-17T00:26:31Z) - Finite-Time Analysis of Temporal Difference Learning: Discrete-Time
Linear System Perspective [3.5823366350053325]
TD-learning is a fundamental algorithm in the field of reinforcement learning (RL)
Recent research has uncovered guarantees concerning its statistical efficiency by developing finite-time error bounds.
arXiv Detail & Related papers (2022-04-22T03:21:30Z) - What Makes Good Contrastive Learning on Small-Scale Wearable-based
Tasks? [59.51457877578138]
We study contrastive learning on the wearable-based activity recognition task.
This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
arXiv Detail & Related papers (2022-02-12T06:10:15Z) - Goal Agnostic Planning using Maximum Likelihood Paths in Hypergraph
World Models [1.370633147306388]
We present a hypergraph-based machine learning algorithm, a datastructure--driven maintenance method, and a planning algorithm based on a probabilistic application of Dijkstra's algorithm.
We prove that the algorithm determines optimal solutions within the problem space, mathematically bound learning performance, and supply a mathematical model analyzing system state progression through time.
arXiv Detail & Related papers (2021-10-18T16:22:33Z) - Model-Augmented Actor-Critic: Backpropagating through Paths [81.86992776864729]
Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator.
We show how to make more effective use of the model by exploiting its differentiability.
arXiv Detail & Related papers (2020-05-16T19:18:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.