Alireza F. Pour
4 papers · 2023–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Research topics
Keywords
sample complexity
(3)
pac learning
(2)
stochastic process
(1)
hypothesis class
(1)
generalization bound
(1)
marginal distribution
(1)
recurrent neural network
(1)
local differential privacy
(1)
distribution estimation
(1)
total variation distance
(1)
interactive algorithm
(1)
sigmoid activation
(1)
hypothesis selection
(1)
learning paradigm
(1)
statistical query algorithm
(1)
instance-optimal learning
(1)
semi-supervised learning
(1)
data-dependent learning
(1)
uniform convergence
(1)
Papers
A Novel Data-Dependent Learning Paradigm for Large Hypothesis Classes
ALT 2026
Relatively Smart: A New Approach for Instance-Optimal Learning
COLT 2026
Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
COLT 2024
On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences
NeurIPS 2023