Search Results for author:
Found 7 papers, 0 papers with code
Asymptotic Optimality for Decentralised Bandits
In fact, our regret guarantee matches the asymptotically optimal rate achievable in the full communication setting.
Optimal subgroup selection
We formulate the problem as one of constrained optimisation, where we seek a low-complexity, data-dependent selection set on which, with a guaranteed probability, the regression function is uniformly at least as large as the threshold; subject to this constraint, we would like the region to contain as much mass under the marginal feature distribution as possible.
Adaptive transfer learning
In transfer learning, we wish to make inference about a target population when we have access to data both from the distribution itself, and from a different but related source distribution.
Statistical optimality conditions for compressive ensembles
For each of these tasks, our strategy is to develop a tight upper bound on the compressibility function, and by doing so we discover distributional conditions of geometric nature under which the compressive algorithm attains minimax-optimal rates up to at most poly-logarithmic factors.
Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise
We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities.
Classification with unknown class-conditional label noise on non-compact feature spaces
In order to obtain finite sample rates, previous approaches to classification with unknown class-conditional label noise have required that the regression function is close to its extrema on sets of large measure.
Modular Autoencoders for Ensemble Feature Extraction
We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks.
