Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning

By Brian Bullins, Elad Hazan, Adam Tauman Kalai, Roi Livni. 2019

21 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Adaptive Gradient-Based Meta-Learning Methods (2019, methodology): “[11] developed an efficient online approach to learning a linear data embedding, but such a setting is distinct from GBML and more closely related to popular shared-representation methods such as ProtoNets [50].”
Provable Representation Learning for Imitation Learning via Bi-level Optimization (2020, background): “Maurer (2009) analyzed linear representation learning, while Bullins et al. (2019); Denevi et al. (2018) provide efficient algorithms to learn linear representations that can reduce sample complexity of a new task.”
Exploiting Shared Representations for Personalized Federated Learning (2021, methodology): “…representation of tasks is a classical approach in multi-task learning [Ando et al., 2005, Balcan et al., 2015, Baxter, 2000, Bengio et al., 2013, Bullins et al., 2019, Denevi et al., 2018, Kong et al., 2020, LeCun et al., 2015, Pontil and Maurer, 2013, Rish et al., 2008, Tripuraneni et al.,…”
Provable Meta-Learning of Linear Representations (2020, background): “4 More recently, Bullins et al. [2019] developed an efficient online learning approach to learn linear embeddings within a discriminative model which can indirectly generalize across a distribution of tasks. The setting is distinct from ours and not directly comparable. However, one principal differ”
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning (2020, background): “Our focus is on a well-studied setting in which tasks such as halfspace learning share a common low-dimensional subspace, with the goal of obtaining sample complexity depending on this sparse structure rather than on the ambient dimension (Maurer, 2009; Maurer & Pontil, 2013; Balcan et al., 2015; De”