Sham M. Kakade

Computer Science · Physical Sciences

66h-index19.6kcitations349works0.62yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Machine Learning and Algorithms(75), Advanced Bandit Algorithms Research(61), Sparse and Compressive Sensing Techniques(60), Stochastic Gradient Optimization Techniques(59), Reinforcement Learning in Robotics(53)

Publications349 total

GQ-VAE: A gated quantized VAE for learning variable length tokens
arXiv (Cornell University)·2025Open Access
GQ-VAE: A gated quantized VAE for learning variable length tokens
ArXiv.org·2025Open Access
The Emergence of Complex Behavior in Large-Scale Ecological Environments
arXiv (Cornell University)·2025Open Access
Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise
arXiv (Cornell University)·2025Open Access
The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
arXiv (Cornell University)·2025Open Access
LOTION: Smoothing the Optimization Landscape for Quantized Training
arXiv (Cornell University)·2025Open Access
Fine-Tuning Masked Diffusion for Provable Self-Correction
arXiv (Cornell University)·2025Open Access
Selective Underfitting in Diffusion Models
arXiv (Cornell University)·2025Open Access
Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization
arXiv (Cornell University)·2025Open Access
Any-Order Flexible Length Masked Diffusion
arXiv (Cornell University)·2025Open Access
Using cognitive models to reveal value trade-offs in language models
arXiv (Cornell University)·2025Open Access
Characterization and Mitigation of Training Instabilities in Microscaling Formats
arXiv (Cornell University)·2025Open Access
A Simplified Analysis of SGD for Linear Regression with Weight Averaging
arXiv (Cornell University)·2025Open Access
Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
arXiv (Cornell University)·2025Open Access
Interpreting the linear structure of vision-language model embedding spaces
arXiv (Cornell University)·2025Open Access
Data-Efficient Multi-Agent Spatial Planning with LLMs
arXiv (Cornell University)·2025Open Access
Random Scaling of Emergent Capabilities
arXiv (Cornell University)·2025Open Access
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
arXiv (Cornell University)·2025Open Access
Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants
arXiv (Cornell University)·2025Open Access
Soup to go: mitigating forgetting during continual learning with model averaging
arXiv (Cornell University)·2025Open Access
page 1 of 18Next →

Frequent Co-authors

Daniel Hsu(14), John Langford(7), Peter Dayan(4), Animashree Anandkumar(4), Rong Ge(4), Dean P. Foster(4), Karthik Sridharan(3), Ambuj Tewari(3), Rong Ge(3), Praneeth Netrapalli(3), Niranjan Srinivas(2), Andreas Krause(2), Matthias Seeger(2), Matus Telgarsky(2), Varsha Dani(2), Thomas P. Hayes(2), Tong Zhang(2), Tong Zhang(2), Chi Jin(2), Michael I. Jordan(2)