Regret to the best vs. regret to the average
By Eyal Even-Dar, Michael Kearns, Yishay Mansour, Jennifer Wortman Vaughan. 2007
38 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Suriya Gunasekar
- Nati Srebro
- Avrim Blum
- Gergely Neu
- Thodoris Lykouris
- Alessandro Lazaric
- Amir Sani
- Behnam Neyshabur
In Computer Networks and Communications
- Nati Srebro
- Gergely Neu
- Thodoris Lykouris
- Alessandro Lazaric
- Amir Sani
- Jakub Konecný
- Martin Takác
- Martin Jaggi
In Management Science and Operations Research
- Avrim Blum
- Nati Srebro
- Gergely Neu
- Thodoris Lykouris
- Alessandro Lazaric
- Suriya Gunasekar
- Amir Sani
- Martin Jaggi
Citations in the corpus
- Semi-Cyclic Stochastic Gradient Descent (2019, neutral): “Such a result has been previously shown in Even-Dar et al. (2008); Sani et al. (2014), building on a lemma of Cesa-Bianchi et al. (2007).”
- On preserving non-discrimination when combining expert advice (2018, methodology): “In fact, this property holds more generally by online learning algorithms with optimal regret guarantees [14].”
- Exploiting easy data in online optimization (2014, methodology): “P ROD algorithm originally proposed by Even-Dar et al. [10]: This variant of P ROD includes the benchmark B in ∆ N as an additional expert and performs P ROD updates for each base expert using the difference between the expert and benchmark losses.”