Sam Duffield
@Sam_Duffield
Followers
499
Following
1K
Media
11
Statuses
99
So happy to release posteriors 𝞡. We've carefully designed the package to be easily extensible, come tell us about your favourite method or application!. Open source, scalable, uncertainty quantification FTW 🥳.
github.com
Uncertainty quantification with PyTorch. Contribute to normal-computing/posteriors development by creating an account on GitHub.
4
16
144
RT @MaxAifer: The era of Physics-based ASICs has arrived. On the surface, computing infrastructure seems unready to meet the demands of AI….
0
36
0
RT @thomasahle: VerilogEval is an odd coding dataset - it gives the agent access to the golden testbench, which you will use to evaluate th….
0
7
0
RT @GhugareRaj: Normalizing Flows (NFs) check all the boxes for RL: exact likelihoods (imitation learning), efficient sampling (real-time c….
0
18
0
You may think it’s “I use AI” but really it’s “AI uses me”.
It's already the case that people's free will gets hijacked by screens for hours a day, with lots of negative consequences. AI video can make this worse, since it's directly optimizable. AI video has positive uses, but most of it will be fast food for the mind.
0
0
0
RT @jxbz: @LucaAmb @Cohere_Labs @ml_collective Hmm. To me it makes sense that first-order methods are ones that use first derivatives and a….
0
1
0
RT @sp_monte_carlo: @xidulu Always a bit funny to me how the interpretation of "second-order optimisation" is not as narrowly-defined as on….
0
1
0
RT @NormalComputing: posteriors 𝞡, our open source Python library for Bayesian computation, will be presented at #ICLR2025! posteriors prov….
0
11
0
We've also updated the paper and made some cool updates to the library 😎. Paper: Repo:
0
0
3
posteriors 𝞡 published at ICLR!. I’ll be in Singapore next week, let’s chat all things scalable Bayesian learning! 🇸🇬👋.
4
10
45
RT @FarisSbahi: Come out and join us, so we can talk about physical world AI and thermodynamic chips. Looking forward to hosting with @nath….
0
13
0
RT @ColesThermoAI: Really exciting progress in silicon happening now at @NormalComputing. Check out Zach's blog post to read more about wha….
0
3
0
RT @blip_tm: during NYC deep tech week, i gave a talk about how @NormalComputing is scaling our thermodynamic computing paradigm to tackle….
0
10
0
So simple! . Normally, we order our minibatches like.a, b, c, . , [shuffle], new_a, new_b, new_c, . but instead, if we do.a, b, c, . , [reverse], . , c, b, a, [shuffle], new_a, new_b, . The RMSE of stochastic gradient descent reduces from O(h) to O(h²)
1
0
10
RT @KaelanDon: Check out our new paper on thermodynamic optimization! 🔥. We show how K-FAC, a powerful and scalable second-order optimizer,….
0
5
0
RT @LucaAmb: @docmilanfar @Magnyz I think that Kalman filters are one of the few things that are genuinely much easier to understand from a….
0
3
0
0
1
9
Thermo Matrix Exponentials has been published in Physical Review Research 🔥. On a thermodynamic computer, the matrix exponential occurs very naturally through the temporal covariance driven by the noise - a polynomial speedup over digital computers!.
journals.aps.org
Thermodynamic computing exploits fluctuations and dissipation in physical systems to efficiently solve various mathematical problems. It was recently shown that certain linear algebra problems can be...
2
17
78
I somehow lost the markdown for this so I asked GPT-4o to recover it from the image. Not only did it do a perfect job of the latex, formatting etc it also silently corrected the error/typo in the definition of V.
An equally brilliant solution comes to us from @Sam_Duffield, who deploys a kind of statistical voodoo to reach the goal
0
0
4
RT @MaxAifer: An equally brilliant solution comes to us from @Sam_Duffield, who deploys a kind of statistical voodoo to reach the goal http….
0
1
0