Search Results for author:
Found 26 papers, 11 papers with code
Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
To overcome this limitation, we introduce a novel training scheme that enables RL algorithms to efficiently learn a concept-based policy by only querying humans to label a small set of data, or in the extreme case, without any human labels.
Meta-Analysis with Untrusted Data
[See paper for full abstract] Meta-analysis is a crucial tool for answering scientific questions.
Successor Feature Sets: Generalizing Successor Representations Across Policies
They also form a natural bridge between model-based and model-free RL methods: like the former they make predictions about future experiences, and like the latter they allow efficient prediction of total discounted rewards.
Understanding and Mitigating Accuracy Disparity in Regression
With the widespread deployment of large-scale prediction systems in high-stakes domains, e. g., face recognition, criminal justice, etc., disparity in prediction accuracy between different demographic subgroups has called for fundamental understanding on the source of such disparity and algorithmic intervention to mitigate it.
Fundamental Limits and Tradeoffs in Invariant Representation Learning
A wide range of machine learning applications such as privacy-preserving learning, algorithmic fairness, and domain adaptation/generalization among others, involve learning invariant representations of the data that aim to achieve two competing goals: (a) maximize information or accuracy with respect to a target response, and (b) maximize invariance or independence with respect to a set of protected features (e. g., for fairness, privacy, etc).
An Empirical Investigation of Beam-Aware Training in Supertagging
This approach leads to mismatches as, during training, the model is not exposed to its mistakes and does not use beam search.
Conditional Learning of Fair Representations
We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting.
Adversarial Privacy Preservation under Attribute Inference Attack
With the prevalence of machine learning services, crowdsourced data containing sensitive information poses substantial privacy challenges.
Learning Neural Networks with Adaptive Regularization
Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis.
Inherent Tradeoffs in Learning Fair Representations
On the upside, we prove that if the group-wise Bayes optimal classifiers are close, then learning fair representations leads to an alternative notion of fairness, known as the accuracy parity, which states that the error rates are close between groups.
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
Meanwhile, it is clear that in general there is a tension between minimizing information leakage and maximizing task accuracy.
On Learning Invariant Representation for Domain Adaptation
Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target.
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks.
Adversarial Multiple Source Domain Adaptation
In this paper we propose new generalization bounds and algorithms under both classification and regression settings for unsupervised multiple source domain adaptation.
Ranked #3 on
Domain Adaptation
on GTA5+Synscapes to Cityscapes
Learning Beam Search Policies via Imitation Learning
Beam search is widely used for approximate decoding in structured prediction problems.
Dual Policy Iteration
Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e. g., ExIt from [2], AlphaGo-Zero from [27]).
Multiple Source Domain Adaptation with Adversarial Learning
We propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances.
Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
As a step toward bridging the gap, we propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances.
Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
We demonstrate that AggreVaTeD --- a policy gradient extension of the Imitation Learning (IL) approach of (Ross & Bagnell, 2014) --- can leverage such an oracle to achieve faster and better solutions with less training data than a less-informed Reinforcement Learning (RL) technique.
An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems
We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations.
Constant Size Molecular Descriptors For Use With Machine Learning
A set of molecular descriptors whose length is independent of molecular size is developed for machine learning models that target thermodynamic and electronic properties of molecules.
Galerkin Methods for Complementarity Problems and Variational Inequalities
One promising idea is Galerkin approximation, in which we search for the best answer within the span of a given set of basis functions.
Predictive State Temporal Difference Learning
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification.
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i. i. d.
Reduced-Rank Hidden Markov Models
We introduce the Reduced-Rank Hidden Markov Model (RR-HMM), a generalization of HMMs that can model smooth state evolution as in Linear Dynamical Systems (LDSs) as well as non-log-concave predictive distributions as in continuous-observation HMMs.
