Sign in

Daniel Augusto

@spectral.space
108 followers 402 following 44 posts

PhD student at UCL. Working on Gaussian Processes. I love everything mathy, videogames, and language. 🇧🇷 He/Ele/Él Also as @spectraldani@sigmoid.social

PostsRepliesMedia
Daniel Augusto @spectral.space · 23/04/2026
#cambridge #photography
020
Daniel Augusto @spectral.space · 12/03/2026
#photography #london
050
Daniel Augusto @spectral.space · 15/02/2026
#photogtaphy #fortaleza
010
Daniel Augusto @spectral.space · 05/01/2026
#photography #fortaleza
020
Daniel Augusto @spectral.space · 02/01/2026
#photography #macao
020
Daniel Augusto @spectral.space · 29/12/2025
#photography #macau
020
Daniel Augusto @spectral.space · 29/12/2025
#photography
Night sky in Brazil showing some stars -- with focus on what I believe to be orion's belt
040
Daniel Augusto @spectral.space · 29/12/2025
Sorry if you have already settled on what to do, but in case it helps anyone else: Pinyin is the last keyboard for TC (TW) on Gboard or you can swap a SC to TC from settings ~
110
Daniel Augusto @spectral.space · 24/12/2025
the tree of shared characters between China, Japan, and Korea was also very cute
A wooden model of a tree with pixelated kanji made with beadsA flier explaining what are the 807 shared characters between China, Japan and Korea.The characters 太 and 文The characters 外, 年 ,中, and 仁
010
Daniel Augusto @spectral.space · 24/12/2025
The best thing of getting a Chinese name is that you can find your name in the kanji wall~
a photo of myself on the kanji dictionary's kanji wall showing the character 浦
210
Daniel Augusto @spectral.space · 15/10/2025
#photography #london
060
Daniel Augusto @spectral.space · 12/10/2025
#photography #wales
080
Daniel Augusto @spectral.space · 11/04/2025
♂️⬅️♊
Photo of the night sky in London with Mars and the two brightest stars of the Gemini constellation. The stars seems to lie on the same line.
000
Daniel Augusto @spectral.space · 13/12/2024
Are you using Bayesian models to infer discrete parameters, like phylogenetic trees, but don't want to keep growing your dataset as new observations arrive? Come join me and Diego ( weakly-informative.github.io ) to learn more at the #NeurIPS2024 11am poster session in the East Exhibit Hall #4010.
A screenshot of our paper, by Tiago da Silva, me, and Diego Mesquita. Abstract: Bayes' rule naturally allows for inference refinement in a streaming fashion, without the need to recompute posteriors from scratch whenever new data arrives. In principle, Bayesian streaming is straightforward: we update our prior with the available data and use the resulting posterior as a prior when processing the next data chunk. In practice, however, this recipe entails i) approximating an intractable posterior at each time step; and ii) encapsulating results appropriately to allow for posterior propagation. For continuous state spaces, variational inference (VI) is particularly convenient due to its scalability and the tractability of variational posteriors, For discrete state spaces, however, state-of-the-art VI results in analytically intractable approximations that are ill-suited for streaming settings. To enable streaming Bayesian inference over discrete parameter spaces, we propose streaming Bayes GFlowNets (abbreviated as SB-GFlowNets) by leveraging the recently proposed GFlowNets -- a powerful class of amortized samplers for discrete compositional objects. Notably, SB-GFlowNet approximates the initial posterior using a standard GFlowNet and subsequently updates it using a tailored procedure that requires only the newly observed data. Our case studies in linear preference learning and phylogenetic inference showcase the effectiveness of SB-GFlowNets in sampling from an unnormalized posterior in a streaming setting. As expected, we also observe that SB-GFlowNets is significantly faster than repeatedly training a GFlowNet from scratch to sample from the full posterior.
120
Daniel Augusto @spectral.space · 13/12/2024
#photography #vancouver
0110
Daniel Augusto @spectral.space · 11/12/2024
#photography #vancouver #NeurIPS #NeurIPS2024
A view of Vancouver with a calm waterfront in the foreground, buildings lining the shore, and a forested mountain range in the background topped with patches of snow.
050
Daniel Augusto @spectral.space · 04/12/2024
#photography #bath
An evening scene showing a calm river reflecting soft lights from nearby street lamps and houses. The foreground features trees framing the view, while in the distance, a small bridge and hillside buildings are visible. The sky above is painted in light blue with delicate, wispy pink clouds, contrasting the darker, shadowed landscape below.
020
Daniel Augusto @spectral.space · 03/12/2024
#london
A close up shot of a next train indicator in a London train station. It shows that the next train to London St. Pancras will arrive in 1158 minutes.
000
Daniel Augusto @spectral.space · 02/12/2024
#photography #london
A photo of some woods around London. The floor is brown-ish due to fallen leaves while narrow trunk trees are seen all around, these trees have green moss in their trunks and eventually color the upper side of the photo with green.
0101
Daniel Augusto @spectral.space · 29/11/2024
#photography #london
Photo of the statue of George I atop the spire of St George's Church. It depicts the king pointing down with what I believe are Roman clothes. It's a clear day with almost no clouds.
040
Daniel Augusto @spectral.space · 28/11/2024
#photography #kyoto
030
Daniel Augusto @spectral.space · 26/11/2024
#photography #london
060
Daniel Augusto @spectral.space · 25/11/2024
#photography #london
050
Daniel Augusto @spectral.space · 24/11/2024
#photography #london
080
Daniel Augusto @spectral.space · 20/11/2024
000
Daniel Augusto @spectral.space · 19/11/2024
010
Daniel Augusto @spectral.space · 18/11/2024
#london
000