Alireza Makhzani
14 papers · 2015–2024 · 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 ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (31) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🧭
Keyword Pioneer
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(78)
Venues
Top co-authors
Research topics
Machine Learning
(13)
Deep Learning
(9)
Optimization & Theory
(9)
Models
(6)
Mathematics & Optimization
(4)
Application Areas
(3)
Core Methods
(3)
Learning Types
(3)
Computer Science
(2)
Architectures
(2)
Bayesian & Probabilistic
(2)
Foundations
(2)
Mathematics
(2)
Optimization
(2)
Artificial Intelligence
(1)
Keywords
generative adversarial network
(3)
bits-back coding
(3)
variational inference
(3)
optimal transport
(2)
deep learning
(2)
lossless compression
(2)
variational autoencoder
(2)
similarity search
(1)
image reconstruction
(1)
image classification
(1)
model evaluation
(1)
kl divergence
(1)
marginal likelihood
(1)
monte carlo estimation
(1)
feature learning
(1)
sequential monte carlo
(1)
mutual information
(1)
hierarchical representation
(1)
log-partition function
(1)
importance sampling
(1)
Papers
A Computational Framework for Solving Wasserstein Lagrangian Flows
ICML 2024
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
ICML 2024
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
ICML 2024
Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
NeurIPS 2024
Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
ICML 2024
Action Matching: Learning Stochastic Dynamics from Samples
ICML 2023
One-Shot Compression of Large Edge-Exchangeable Graphs using Bits-Back Coding
ICML 2023
Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation
NeurIPS 2023
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
ICLR 2022
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
ICML 2021
Variational Model Inversion Attacks
NeurIPS 2021
Evaluating Lossy Compression Rates of Deep Generative Models
ICML 2020
PixelGAN Autoencoders
NeurIPS 2017
Winner-Take-All Autoencoders
NeurIPS 2015