Search Results for author:
Found 13 papers, 1 papers with code
Distribution Embedding Networks for Generalization from a Diverse Set of Classification Tasks
We propose Distribution Embedding Networks (DEN) for classification with small data.
Optimizing Black-box Metrics with Iterative Example Weighting
We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix.
Distribution Embedding Network for Meta-Learning with Variable-Length Input
We propose Distribution Embedding Network (DEN) for meta-learning, which is designed for applications where both the distribution and the number of features could vary across tasks.
Optimizing Black-box Metrics with Adaptive Surrogates
We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surrogates.
Constrained Interacting Submodular Groupings
We introduce the problem of grouping a finite ground set into blocks where each block is a subset of the ground set and where: (i) the blocks are individually highly valued by a submodular function (both robustly and in the average case) while satisfying block-specific matroid constraints; and (ii) block scores interact where blocks are jointly scored highly, thus making the blocks mutually non-redundant.
Proxy Fairness
We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime.
Metric-Optimized Example Weights
Real-world machine learning applications often have complex test metrics, and may have training and test data that are not identically distributed.
Fast and Flexible Monotonic Functions with Ensembles of Lattices
For many machine learning problems, there are some inputs that are known to be positively (or negatively) related to the output, and in such cases training the model to respect that monotonic relationship can provide regularization, and makes the model more interpretable.
Launch and Iterate: Reducing Prediction Churn
Practical applications of machine learning often involve successive training iterations with changes to features and training examples.
Non-Deterministic Policies in Markovian Decision Processes
Although conventional methods in reinforcement learning have proved to be useful in problems concerning sequential decision-making, they cannot be applied in their current form to decision support systems, such as those in medical domains, as they suggest policies that are often highly prescriptive and leave little room for the users input.
Efficient Learning and Planning with Compressed Predictive States
Predictive state representations (PSRs) offer an expressive framework for modelling partially observable systems.
Bellman Error Based Feature Generation using Random Projections on Sparse Spaces
This paper addresses the problem of automatic generation of features for value function approximation in reinforcement learning.
PAC-Bayesian Policy Evaluation for Reinforcement Learning
PAC-Bayesian methods overcome this problem by providing bounds that hold regardless of the correctness of the prior distribution.
