Search Results for author:
Found 11 papers, 0 papers with code
On Correcting Inputs: Inverse Optimization for Online Structured Prediction
Algorithm designers typically assume that the input data is correct, and then proceed to find "optimal" or "sub-optimal" solutions using this input data.
Improving Online Algorithms via ML Predictions
In this work we study the problem of using machine-learned predictions to improve performance of online algorithms.
Efficient Rematerialization for Deep Networks
When training complex neural networks, memory usage can be an important bottleneck.
Online Learning with Imperfect Hints
We consider a variant of the classical online linear optimization problem in which at every step, the online player receives a "hint" vector before choosing the action for that round.
Online Linear Optimization with Many Hints
We study an online linear optimization (OLO) problem in which the learner is provided access to $K$ "hint" vectors in each round prior to making a decision.
Strategy-proof and Envy-free Mechanisms for House Allocation
In this paper, we are motivated by the following question: Is there a strategy-proof and envy-free random assignment mechanism more efficient than equal division?
Upper Confidence Bounds for Combining Stochastic Bandits
We provide a simple method to combine stochastic bandit algorithms.
Logarithmic Regret from Sublinear Hints
We consider the online linear optimization problem, where at every step the algorithm plays a point $x_t$ in the unit ball, and suffers loss $\langle c_t, x_t\rangle$ for some cost vector $c_t$ that is then revealed to the algorithm.
Online Knapsack with Frequency Predictions
There has been recent interest in using machine-learned predictions to improve the worst-case guarantees of online algorithms.
Parsimonious Learning-Augmented Caching
Learning-augmented algorithms -- in which, traditional algorithms are augmented with machine-learned predictions -- have emerged as a framework to go beyond worst-case analysis.
Optimizing Memory Mapping Using Deep Reinforcement Learning
We also introduce a Reinforcement Learning agent, mallocMuZero, and show that it is capable of playing this game to discover new and improved memory mapping solutions that lead to faster execution times on real ML workloads on ML accelerators.
