Search Results for author:
Found 9 papers, 6 papers with code
Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling.
Ranked #34 on
Language Modelling
on Penn Treebank (Word Level)
Mostly Exploration-Free Algorithms for Contextual Bandits
We prove that this algorithm is rate optimal without any additional assumptions on the context distribution or the number of arms.
Matrix Completion Methods for Causal Panel Data Models
In this paper we study methods for estimating causal effects in settings with panel data, where some units are exposed to a treatment during some periods and the goal is estimating counterfactual (untreated) outcomes for the treated unit/period combinations.
Statistics Theory Econometrics Statistics Theory
Non-Parametric Inference Adaptive to Intrinsic Dimension
We show that if the intrinsic dimension of the covariate distribution is equal to $d$, then the finite sample estimation error of our estimator is of order $n^{-1/(d+2)}$ and our estimate is $n^{1/(d+2)}$-asymptotically normal, irrespective of $D$.
The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
This finding diverges from the notion of free exploration, which relates to covariate variation, as recently discussed in contextual bandit literature.
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
We study the structure of regret-minimizing policies in the {\em many-armed} Bayesian multi-armed bandit problem: in particular, with $k$ the number of arms and $T$ the time horizon, we consider the case where $k \geq \sqrt{T}$.
Batched Neural Bandits
In many sequential decision-making problems, the individuals are split into several batches and the decision-maker is only allowed to change her policy at the end of batches.
Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls
We investigate the optimal design of experimental studies that have pre-treatment outcome data available.
Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms
We present online learning algorithms for any possible value of the evolution rate $\lambda$ and we show the robustness of our results to various model misspecifications.
