Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model
Paper ā¢ 2609.06008 ā¢ Published ā¢ 16 ā¢
4
Roberto Tacconelli PRO
robtacconelli
AI & ML interests
None yet
Recent Activity
commentedon a paper 1 day ago
Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model authored a paper 1 day ago
Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation ModelOrganizations
commented a
paper 1 day ago
authored a
paper 1 day ago
upvoted a paper 1 day ago
submitted a
paper to Daily Papers 1 day ago
liked a
Space 4 days ago
reacted to their post with š„ 4 days ago
Post
1872
š§© Ever dreamed of parallel programming in a few clicks? Tolquane: draw a Python pipeline in your browser, run it on threads, processes or a cluster - and it never hangs
What if high-performance computing started with placing blocks - and the result stayed plain Python you can run anywhere?
Tolquane is a library of composable building blocks (nodes, pipelines, farms, all-to-all, feedback loops) with a web editor on top. One graph, four runtimes: threads, child processes, coroutines, TCP across machines. Every channel is bounded, every deadlock is reported by name, every error cancels the run.
What's inside
- Tolquane Web: a canvas that writes the Python file, and a code editor that redraws the canvas. Run a flow and watch items, queue depth and busy time on every stage; tap any edge to see what flows through it.
- AI builder: describe the flow in one sentence; it writes, checks, runs and improves it, you apply the diff.
- Schedules with cron presets, webhooks, mail and retries. Git history of every flow. Users and roles.
-
Numbers: 5.5Ć on 8 workers for CPU-bound Python (processes runtime), 5.6Ć on free-threaded 3.14t, 1M items over TCP in 3.5 s.
š Try it now, nothing to install (sign in as demo / tolquane): robtacconelli/tolquane
š» Code: https://github.com/robtacconelli/Tolquane
š¦ pip install "tolquane[web]" && tolquane web
š Docs: https://robtacconelli.github.io/Tolquane/
Apache-2.0, Python 3.11+, no dependencies for the library itself. Try it, break it, tell me what you'd build with it - ā appreciated!
What if high-performance computing started with placing blocks - and the result stayed plain Python you can run anywhere?
Tolquane is a library of composable building blocks (nodes, pipelines, farms, all-to-all, feedback loops) with a web editor on top. One graph, four runtimes: threads, child processes, coroutines, TCP across machines. Every channel is bounded, every deadlock is reported by name, every error cancels the run.
What's inside
- Tolquane Web: a canvas that writes the Python file, and a code editor that redraws the canvas. Run a flow and watch items, queue depth and busy time on every stage; tap any edge to see what flows through it.
- AI builder: describe the flow in one sentence; it writes, checks, runs and improves it, you apply the diff.
- Schedules with cron presets, webhooks, mail and retries. Git history of every flow. Users and roles.
-
tq.optimize fuses stages into farm ends and cuts threads; tolquane launch starts every host from one deploy file.Numbers: 5.5Ć on 8 workers for CPU-bound Python (processes runtime), 5.6Ć on free-threaded 3.14t, 1M items over TCP in 3.5 s.
š Try it now, nothing to install (sign in as demo / tolquane): robtacconelli/tolquane
š» Code: https://github.com/robtacconelli/Tolquane
š¦ pip install "tolquane[web]" && tolquane web
š Docs: https://robtacconelli.github.io/Tolquane/
Apache-2.0, Python 3.11+, no dependencies for the library itself. Try it, break it, tell me what you'd build with it - ā appreciated!
- 1 reply
published an article 4 days ago
Article
Ever dreamed of parallel programming in a few clicks? Meet Tolquane
robtacconelli
ā¢ posted an update 4 days ago
Post
1872
š§© Ever dreamed of parallel programming in a few clicks? Tolquane: draw a Python pipeline in your browser, run it on threads, processes or a cluster - and it never hangs
What if high-performance computing started with placing blocks - and the result stayed plain Python you can run anywhere?
Tolquane is a library of composable building blocks (nodes, pipelines, farms, all-to-all, feedback loops) with a web editor on top. One graph, four runtimes: threads, child processes, coroutines, TCP across machines. Every channel is bounded, every deadlock is reported by name, every error cancels the run.
What's inside
- Tolquane Web: a canvas that writes the Python file, and a code editor that redraws the canvas. Run a flow and watch items, queue depth and busy time on every stage; tap any edge to see what flows through it.
- AI builder: describe the flow in one sentence; it writes, checks, runs and improves it, you apply the diff.
- Schedules with cron presets, webhooks, mail and retries. Git history of every flow. Users and roles.
-
Numbers: 5.5Ć on 8 workers for CPU-bound Python (processes runtime), 5.6Ć on free-threaded 3.14t, 1M items over TCP in 3.5 s.
š Try it now, nothing to install (sign in as demo / tolquane): robtacconelli/tolquane
š» Code: https://github.com/robtacconelli/Tolquane
š¦ pip install "tolquane[web]" && tolquane web
š Docs: https://robtacconelli.github.io/Tolquane/
Apache-2.0, Python 3.11+, no dependencies for the library itself. Try it, break it, tell me what you'd build with it - ā appreciated!
What if high-performance computing started with placing blocks - and the result stayed plain Python you can run anywhere?
Tolquane is a library of composable building blocks (nodes, pipelines, farms, all-to-all, feedback loops) with a web editor on top. One graph, four runtimes: threads, child processes, coroutines, TCP across machines. Every channel is bounded, every deadlock is reported by name, every error cancels the run.
What's inside
- Tolquane Web: a canvas that writes the Python file, and a code editor that redraws the canvas. Run a flow and watch items, queue depth and busy time on every stage; tap any edge to see what flows through it.
- AI builder: describe the flow in one sentence; it writes, checks, runs and improves it, you apply the diff.
- Schedules with cron presets, webhooks, mail and retries. Git history of every flow. Users and roles.
-
tq.optimize fuses stages into farm ends and cuts threads; tolquane launch starts every host from one deploy file.Numbers: 5.5Ć on 8 workers for CPU-bound Python (processes runtime), 5.6Ć on free-threaded 3.14t, 1M items over TCP in 3.5 s.
š Try it now, nothing to install (sign in as demo / tolquane): robtacconelli/tolquane
š» Code: https://github.com/robtacconelli/Tolquane
š¦ pip install "tolquane[web]" && tolquane web
š Docs: https://robtacconelli.github.io/Tolquane/
Apache-2.0, Python 3.11+, no dependencies for the library itself. Try it, break it, tell me what you'd build with it - ā appreciated!
- 1 reply
updated a
Space 4 days ago
published a
Space 4 days ago
authored a
paper 4 months ago
upvoted a paper 4 months ago
submitted a
paper to Daily Papers 4 months ago
liked a
model 5 months ago
authored a
paper 6 months ago
upvoted 2
papers 6 months ago
submitted a
paper to Daily Papers 6 months ago
liked a
Space 6 months ago
reacted to their post with š¤Æ 6 months ago
Post
3731
š§¬ Midicoth: diffusion-based lossless compression ā no neural net, no GPU, no training data
What if reverse diffusion could compress text ā without a neural network?
Midicoth brings score-based denoising into classical compression. It treats prior smoothing as forward noise and reverses it with Tweedie's formula on a binary tree ā 3 denoising steps, James-Stein shrinkage, applied after all model blending. ~2,000 lines of C, single CPU core.
Beats every dictionary compressor we tested:
enwik8 (100 MB) ā 1.753 bpb (ā11.9% vs xz, ā15% vs Brotli, ā24.5% vs bzip2)
alice29.txt ā 2.119 bpb (ā16.9% vs xz)
Outperforms xz, zstd, Brotli, bzip2, gzip on all inputs
PAQ/CMIX still win with hundreds of models + LSTMs. LLM compressors win with pre-trained knowledge. Midicoth closes the gap with pure statistics ā no mixer, no gradient descent, just counting.
The Tweedie denoising layer adds 2.3ā2.7% on every file tested ā the most consistent component in the ablation. Adding SSE or logistic mixers made things worse. In the online setting, count-based beats gradient-based.
No external dependencies. Fully deterministic. Bit-exact encode/decode. ~60 KB/s throughput.
š» Code: https://github.com/robtacconelli/midicoth
š Paper: Micro-Diffusion Compression -- Binary Tree Tweedie Denoising for Online Probability Estimation (2603.08771)
ā Space: robtacconelli/midicoth
If you ever wondered whether diffusion ideas belong in data compression ā here's proof they do. ā appreciated!
What if reverse diffusion could compress text ā without a neural network?
Midicoth brings score-based denoising into classical compression. It treats prior smoothing as forward noise and reverses it with Tweedie's formula on a binary tree ā 3 denoising steps, James-Stein shrinkage, applied after all model blending. ~2,000 lines of C, single CPU core.
Beats every dictionary compressor we tested:
enwik8 (100 MB) ā 1.753 bpb (ā11.9% vs xz, ā15% vs Brotli, ā24.5% vs bzip2)
alice29.txt ā 2.119 bpb (ā16.9% vs xz)
Outperforms xz, zstd, Brotli, bzip2, gzip on all inputs
PAQ/CMIX still win with hundreds of models + LSTMs. LLM compressors win with pre-trained knowledge. Midicoth closes the gap with pure statistics ā no mixer, no gradient descent, just counting.
The Tweedie denoising layer adds 2.3ā2.7% on every file tested ā the most consistent component in the ablation. Adding SSE or logistic mixers made things worse. In the online setting, count-based beats gradient-based.
No external dependencies. Fully deterministic. Bit-exact encode/decode. ~60 KB/s throughput.
š» Code: https://github.com/robtacconelli/midicoth
š Paper: Micro-Diffusion Compression -- Binary Tree Tweedie Denoising for Online Probability Estimation (2603.08771)
ā Space: robtacconelli/midicoth
If you ever wondered whether diffusion ideas belong in data compression ā here's proof they do. ā appreciated!