Transfer Learning via $\ell_1$ Regularization

• URL: http://arxiv.org/abs/2006.14845v1
• Date: Fri, 26 Jun 2020 07:42:03 GMT
• Title: Transfer Learning via $\ell_1$ Regularization
• Authors: Masaaki Takada, Hironori Fujisawa
• Abstract summary: We propose a method for transferring knowledge from a source domain to a target domain. Our method yields sparsity for both the estimates themselves and changes of the estimates. Empirical results demonstrate that the proposed method effectively balances stability and plasticity.
• Score: 9.442139459221785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning algorithms typically require abundant data under a stationary environment. However, environments are nonstationary in many real-world applications. Critical issues lie in how to effectively adapt models under an ever-changing environment. We propose a method for transferring knowledge from a source domain to a target domain via $\ell_1$ regularization. We incorporate $\ell_1$ regularization of differences between source parameters and target parameters, in addition to an ordinary $\ell_1$ regularization. Hence, our method yields sparsity for both the estimates themselves and changes of the estimates. The proposed method has a tight estimation error bound under a stationary environment, and the estimate remains unchanged from the source estimate under small residuals. Moreover, the estimate is consistent with the underlying function, even when the source estimate is mistaken due to nonstationarity. Empirical results demonstrate that the proposed method effectively balances stability and plasticity.

Related papers

• Linear cost and exponentially convergent approximation of Gaussian Matérn processes [43.341057405337295]
  computational cost for inference and prediction of statistical models based on Gaussian processes scales cubicly with the number of observations. We develop a method with linear cost and with a covariance error that decreases exponentially fast in the order $m$ of the proposed approximation. The method is based on an optimal rational approximation of the spectral density and results in an approximation that can be represented as a sum of $m$ independent Markov processes.
  arXiv  Detail & Related papers  (2024-10-16T19:57:15Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance. Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
  We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
  arXiv  Detail & Related papers  (2024-05-09T12:52:22Z)
• Nearest Neighbor Sampling for Covariate Shift Adaptation [7.940293148084844]
  We propose a new covariate shift adaptation method which avoids estimating the weights. The basic idea is to directly work on unlabeled target data, labeled according to the $k$-nearest neighbors in the source dataset. Our experiments show that it achieves drastic reduction in the running time with remarkable accuracy.
  arXiv  Detail & Related papers  (2023-12-15T17:28:09Z)
• Online non-parametric likelihood-ratio estimation by Pearson-divergence functional minimization [55.98760097296213]
  We introduce a new framework for online non-parametric LRE (OLRE) for the setting where pairs of iid observations $(x_t sim p, x'_t sim q)$ are observed over time. We provide theoretical guarantees for the performance of the OLRE method along with empirical validation in synthetic experiments.
  arXiv  Detail & Related papers  (2023-11-03T13:20:11Z)
• Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits [18.982448033389588]
  Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. To account for the effect of different environments during learning and execution, distributionally robust optimization (DRO) methods have been developed. We propose a novel DRO approach that employs the Wasserstein distance instead.
  arXiv  Detail & Related papers  (2023-09-15T20:21:46Z)
• Improved Convergence of Score-Based Diffusion Models via Prediction-Correction [15.772322871598085]
  Score-based generative models (SGMs) are powerful tools to sample from complex data distributions. This paper addresses the issue by considering a version of the popular predictor-corrector scheme. We first estimate the final distribution via an inexact Langevin dynamics and then revert the process.
  arXiv  Detail & Related papers  (2023-05-23T15:29:09Z)
• Environment Invariant Linear Least Squares [18.387614531869826]
  This paper considers a multi-environment linear regression model in which data from multiple experimental settings are collected. We construct a novel environment invariant linear least squares (EILLS) objective function, a multi-environment version of linear least-squares regression.
  arXiv  Detail & Related papers  (2023-03-06T13:10:54Z)
• A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning [113.75991721607174]
  We introduce an interventional prediction module to estimate the probability of two estimated $hatz_i, hatz_j$ belonging to the same environment. We empirically show that $hatZ$ estimated by our method enjoy less redundant information than previous methods.
  arXiv  Detail & Related papers  (2022-06-09T15:01:36Z)
• Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization [101.5159744660701]
  In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. Here, we introduce a new technique for debiasing the local estimates, which leads to both theoretical and empirical improvements in the convergence rate of distributed second order methods.
  arXiv  Detail & Related papers  (2020-07-02T18:08:14Z)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)

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.