Transfer Learning Beyond Bounded Density Ratios

• URL: http://arxiv.org/abs/2403.11963v1
• Date: Mon, 18 Mar 2024 17:02:41 GMT
• Title: Transfer Learning Beyond Bounded Density Ratios
• Authors: Alkis Kalavasis, Ilias Zadik, Manolis Zampetakis,
• Abstract summary: We study the fundamental problem of transfer learning where a learning algorithm collects data from some source distribution $P$ but needs to perform well with respect to a different target distribution $Q$. Our main result is a general transfer inequality over the domain $mathbbRn$, proving that non-trivial transfer learning for low-degrees is possible under very mild assumptions.
• Score: 21.522183597134234
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the fundamental problem of transfer learning where a learning algorithm collects data from some source distribution $P$ but needs to perform well with respect to a different target distribution $Q$. A standard change of measure argument implies that transfer learning happens when the density ratio $dQ/dP$ is bounded. Yet, prior thought-provoking works by Kpotufe and Martinet (COLT, 2018) and Hanneke and Kpotufe (NeurIPS, 2019) demonstrate cases where the ratio $dQ/dP$ is unbounded, but transfer learning is possible. In this work, we focus on transfer learning over the class of low-degree polynomial estimators. Our main result is a general transfer inequality over the domain $\mathbb{R}^n$, proving that non-trivial transfer learning for low-degree polynomials is possible under very mild assumptions, going well beyond the classical assumption that $dQ/dP$ is bounded. For instance, it always applies if $Q$ is a log-concave measure and the inverse ratio $dP/dQ$ is bounded. To demonstrate the applicability of our inequality, we obtain new results in the settings of: (1) the classical truncated regression setting, where $dQ/dP$ equals infinity, and (2) the more recent out-of-distribution generalization setting for in-context learning linear functions with transformers. We also provide a discrete analogue of our transfer inequality on the Boolean Hypercube $\{-1,1\}^n$, and study its connections with the recent problem of Generalization on the Unseen of Abbe, Bengio, Lotfi and Rizk (ICML, 2023). Our main conceptual contribution is that the maximum influence of the error of the estimator $\widehat{f}-f^*$ under $Q$, $\mathrm{I}_{\max}(\widehat{f}-f^*)$, acts as a sufficient condition for transferability; when $\mathrm{I}_{\max}(\widehat{f}-f^*)$ is appropriately bounded, transfer is possible over the Boolean domain.

Related papers

• Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition [71.33787410075577]
  We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses. We propose a new algorithm that attains an $widetildeO(dsqrtHS3K + sqrtHSAK)$ regret with high probability.
  arXiv  Detail & Related papers  (2024-03-07T15:03:50Z)
• Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss [33.18537822803389]
  We show that whenever the topologies of $L2$ and $Psi_p$ are comparable on our hypothesis class $mathscrF$, $mathscrF$ is a weakly sub-Gaussian class. Our result holds whether the problem is realizable or not and we refer to this as a emphnear mixing-free rate, since direct dependence on mixing is relegated to an additive higher order term.
  arXiv  Detail & Related papers  (2024-02-08T18:57:42Z)
• Towards the Fundamental Limits of Knowledge Transfer over Finite Domains [8.575522204707957]
  We show that privileged information at three progressive levels accelerates the transfer. At the first level, only samples with hard labels are known, via which the maximum likelihood estimator attains the minimax rate $sqrt|mathcal Smathcal A|/n$. The third level further equips the student with the soft labels (complete logits) on $mathcal A$ given every sampled input, thereby provably enables the student to enjoy a rate $|mathcal S|/n$ free of $
  arXiv  Detail & Related papers  (2023-10-11T19:30:08Z)
• Depth Dependence of $\mu$P Learning Rates in ReLU MLPs [72.14317069090407]
  We study the dependence on $n$ and $L$ of the maximal update ($mu$P) learning rate. We find that it has a non-trivial dependence of $L$, scaling like $L-3/2.$
  arXiv  Detail & Related papers  (2023-05-13T01:10:49Z)
• Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes [62.90204655228324]
  We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic and a value-optimistic solver.
  arXiv  Detail & Related papers  (2022-10-20T21:32:01Z)
• Locality defeats the curse of dimensionality in convolutional teacher-student scenarios [69.2027612631023]
  We show that locality is key in determining the learning curve exponent $beta$. We conclude by proving, using a natural assumption, that performing kernel regression with a ridge that decreases with the size of the training set leads to similar learning curve exponents to those we obtain in the ridgeless case.
  arXiv  Detail & Related papers  (2021-06-16T08:27:31Z)
• Learning the optimal regularizer for inverse problems [1.763934678295407]
  We consider the linear inverse problem $y=Ax+epsilon$, where $Acolon Xto Y$ is a known linear operator between the separable Hilbert spaces $X$ and $Y$. This setting covers several inverse problems in imaging including denoising, deblurring, and X-ray tomography. Within the classical framework of regularization, we focus on the case where the regularization functional is not given a priori but learned from data.
  arXiv  Detail & Related papers  (2021-06-11T17:14:27Z)
• Hardness of Learning Halfspaces with Massart Noise [56.98280399449707]
  We study the complexity of PAC learning halfspaces in the presence of Massart (bounded) noise. We show that there an exponential gap between the information-theoretically optimal error and the best error that can be achieved by a SQ algorithm.
  arXiv  Detail & Related papers  (2020-12-17T16:43:11Z)
• An Improved Transfer Model: Randomized Transferable Machine [32.50263074872975]
  We propose a new transfer model called Randomized Transferable Machine (RTM) to handle small divergence of domains. Specifically, we work on the new source and target data learned from existing feature-based transfer methods. In principle, the more corruptions are made, the higher the probability of the new target data can be covered by the constructed source data populations.
  arXiv  Detail & Related papers  (2020-11-27T09:37:01Z)
• Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals [49.60752558064027]
  We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. Our lower bounds provide strong evidence that current upper bounds for these tasks are essentially best possible.
  arXiv  Detail & Related papers  (2020-06-29T17:10:10Z)

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.