PhD Candidate, UCSB
Probabilistic computing •
Ising/Boltzmann •
FPGA/CMOS • ML/AI

Navid Aadit giving a talk

View CV

I am a PhD candidate in Electrical & Computer Engineering at the University of California, Santa Barbara (expected Dec 2025).

I work on probabilistic computing with p-bits and extreme-scale distributed architectures, building Ising/Boltzmann machines on CMOS/FPGA platforms and developing hardware–software co-design for scalable multi-chip systems. Applications include combinatorial optimization, energy-based machine learning, AI sampling, and quantum-inspired non-local algorithms.

My recent work scales p-computers across multi-FPGA systems with delay-tolerant communication and balanced partitioning to sustain solution quality at unprecedented sizes.

  • Probabilistic computing
  • Quantum computing
  • Ising/Boltzmann machines
  • Distributed chips
  • FPGA accelerators
  • Energy-based ML

Research Highlights

  • Distributed probabilistic computing — Interconnect multi-FPGA / heterogeneous hardware over ultra-low-latency links; ~1M p-bits scaling.
  • Probabilistic AI & ML — Ising/Boltzmann samplers for generative AI, Bayesian inference, and scalable energy-based ML.
  • Quantum-inspired optimization — Hardware–software co-design blending probabilistic systems with quantum-classical workflows.

Key first-author papers

  • Nature Electronics (2022): Massively parallel probabilistic computing with sparse Ising machines.
  • Nature Communications (2024): All-to-all reconfigurability with sparse & higher-order Ising machines.
  • VLSI Symposium (2023): Accelerating Adaptive Parallel Tempering with FPGA-based p-bits.
  • IEDM (2022): Experimental evaluation of simulated quantum annealing with MTJ-augmented p-bits.
  • IEDM (2021): Computing with invertible logic: Combinatorial optimization with probabilistic bits.

Recognition