Borja Balle
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
- Alex Kurakinonce
- Amer Sinhaonce
- Arun Ganeshonce
all 8 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Private Tuning of LLMs in Practice: From VaultGemma to Custom Fine-Tuning | PEPR '26 | 2026-06-01 |
Claim: Differential Privacy is practical at production scale using JAX Privacy to train and fine-tune Gemma-family models including VaultGemma. Implementation… | ||
| The Privacy Blanket of the Shuffle Model | Privacy and the Science of Data Analysis 2019 | 2019-04-08 |
Claims a single‑message shuffle protocol attains mean squared error Θ(n^{1/3}) (so estimation error Θ(n^{1/6})) with a matching lower bound, and achieves… | ||
| Learning the Privacy-Utility Trade-off with Bayesian Optimization | Data Privacy: From Foundations to Applications (Simons Institute workshop, 2019) | 2019-03-04 |
Implementation uses multi-objective Bayesian optimization with a Gaussian process surrogate and a hypervolume probability of improvement acquisition to map… | ||
| nothing matches | ||