Stochastic optimization problems with nondifferentiable cost functionals

By Dimitri P. Bertsekas. 1973

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. John C. Duchi
2. Michael I. Jordan
3. Yoshua Bengio
4. Francis R. Bach
5. Percy Liang
6. Ruslan Salakhutdinov
7. Sergey Levine
8. Dacheng Tao

Citations in the corpus

• The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle (2013, background): “Since μ is a density with respect to Lebesgue measure, fμ is differentiable [5].”
• Randomized Smoothing for Stochastic Optimization (2011, background): “Clearly, f µ is convex whenever f is convex; moreover, it is known that if µ is a density with respect to Lebesgue measure, then f µ is differentiable [4].”
• Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity (2018, unknown): “[6]).”
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations (2013, result): “Proof of Lemma 12: Since the quantity ‖Z1 + u Z2‖2 has a density with respect to Lebesgue measure, standard results on differentiating through an expectation [38] imply”