Search Results for author:
Found 23 papers, 0 papers with code
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
Compared to the best results for the single-agent setting, our bounds have additional gaps.
Linear Reinforcement Learning with Ball Structure Action Space
We study the problem of Reinforcement Learning (RL) with linear function approximation, i. e. assuming the optimal action-value function is linear in a known $d$-dimensional feature mapping.
Smooth Calibration, Leaky Forecasts, Finite Recall, and Nash Dynamics
We propose to smooth out the calibration score, which measures how good a forecaster is, by combining nearby forecasts.
Forecast Hedging and Calibration
Calibration means that forecasts and average realized frequencies are close.
Deep Inventory Management
This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor lead times, lost sales, correlated demand, and price matching.
"Calibeating": Beating Forecasters at Their Own Game
In order to identify expertise, forecasters should not be tested by their calibration score, which can always be made arbitrarily small, but rather by their Brier score.
A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation
Towards establishing the minimal amount of expert queries needed, we show that, in the same setting, any learner whose exploration budget is polynomially-bounded (in terms of $d, H,$ and $|\mathcal{A}|$) will require at least $\tilde\Omega(\sqrt{d})$ oracle calls to recover a policy competing with the expert's value function.
On Submodular Contextual Bandits
We consider the problem of contextual bandits where actions are subsets of a ground set and mean rewards are modeled by an unknown monotone submodular function that belongs to a class $\mathcal{F}$.
The Benefits of Implicit Regularization from SGD in Least Squares Problems
Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice, which has been hypothesized to play an important role in the generalization of modern machine learning approaches.
Threshold Martingales and the Evolution of Forecasts
In addition to being calibrated, a threshold martingale has quadratic variation that accumulates to a total determined by a quantile of the initial forecast distribution.
What are the Statistical Limits of Offline RL with Linear Function Approximation?
Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies.
Coupled Recurrent Models for Polyphonic Music Composition
This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music.
Large scale canonical correlation analysis with iterative least squares
Canonical Correlation Analysis (CCA) is a widely used statistical tool with both well established theory and favorable performance for a wide range of machine learning problems.
Fast Ridge Regression with Randomized Principal Component Analysis and Gradient Descent
We propose a new two stage algorithm LING for large scale regression problems.
Faster Ridge Regression via the Subsampled Randomized Hadamard Transform
We propose a fast algorithm for ridge regression when the number of features is much larger than the number of observations ($p \gg n$).
One-shot learning and big data with n=2
One of the salient features of our analysis is that the problems studied here are easier when the dimension of $x_i$ is large; in other words, prediction becomes easier when more context is provided.
New Subsampling Algorithms for Fast Least Squares Regression
We address the problem of fast estimation of ordinary least squares (OLS) from large amounts of data ($n \gg p$).
A Spectral Algorithm for Latent Dirichlet Allocation
This work provides a simple and efficient learning procedure that is guaranteed to recover the parameters for a wide class of topic models, including Latent Dirichlet Allocation (LDA).
Stochastic convex optimization with bandit feedback
This paper addresses the problem of minimizing a convex, Lipschitz function $f$ over a convex, compact set $X$ under a stochastic bandit feedback model.
Multi-View Learning of Word Embeddings via CCA
Recently, there has been substantial interest in using large amounts of unlabeled data to learn word representations which can then be used as features in supervised classifiers for NLP tasks.
A Risk Comparison of Ordinary Least Squares vs Ridge Regression
We compare the risk of ridge regression to a simple variant of ordinary least squares, in which one simply projects the data onto a finite dimensional subspace (as specified by a Principal Component Analysis) and then performs an ordinary (un-regularized) least squares regression in this subspace.
