On the Convergence of AdaGrad on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration.
Zijian LiuTa Duy NguyenAlina EneHuy L. NguyenPublished in: CoRR (2022)
Keyphrases
- rates of convergence
- finite sample
- convergence rate
- data sets
- expected values
- sampling rate
- convergence speed
- real time
- rate distortion
- initial conditions
- global convergence
- number of iterations required
- steady state
- convex hull
- sample size
- motion estimation
- asymptotically optimal
- faster convergence
- stochastic approximation
- search engine
- real world
- asymptotic optimality