Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model
Paper • 2609.06008 • Published • 16
AI & ML interests
None defined yet.
Recent Activity
View all activity
robtacconelli
authored a
paper 1 day ago
robtacconelli
submitted a
paper to Daily Papers 2 days ago
robtacconelli
posted an update 4 days ago
Post
1872
🧩 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: 5.5× on 8 workers for CPU-bound Python (processes runtime), 5.6× on free-threaded 3.14t, 1M items over TCP in 3.5 s.
🌐 Try it now, nothing to install (sign in as demo / tolquane): robtacconelli/tolquane
💻 Code: https://github.com/robtacconelli/Tolquane
📦 pip install "tolquane[web]" && tolquane web
📚 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 - ⭐ 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: 5.5× on 8 workers for CPU-bound Python (processes runtime), 5.6× on free-threaded 3.14t, 1M items over TCP in 3.5 s.
🌐 Try it now, nothing to install (sign in as demo / tolquane): robtacconelli/tolquane
💻 Code: https://github.com/robtacconelli/Tolquane
📦 pip install "tolquane[web]" && tolquane web
📚 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 - ⭐ appreciated!
- 1 reply
robtacconelli
authored a
paper 4 months ago
robtacconelli
submitted a
paper to Daily Papers 4 months ago
robtacconelli
authored a
paper 6 months ago
robtacconelli
submitted a
paper to Daily Papers 6 months ago
robtacconelli
posted an update 6 months ago
Post
3731
🧬 Midicoth: diffusion-based lossless compression — no neural net, no GPU, no training data
What if reverse diffusion could compress text — 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 — 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) → 1.753 bpb (−11.9% vs xz, −15% vs Brotli, −24.5% vs bzip2)
alice29.txt → 2.119 bpb (−16.9% 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 — no mixer, no gradient descent, just counting.
The Tweedie denoising layer adds 2.3–2.7% on every file tested — 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.
💻 Code: https://github.com/robtacconelli/midicoth
📄 Paper: Micro-Diffusion Compression -- Binary Tree Tweedie Denoising for Online Probability Estimation (2603.08771)
⭐ Space: robtacconelli/midicoth
If you ever wondered whether diffusion ideas belong in data compression — here's proof they do. ⭐ appreciated!
What if reverse diffusion could compress text — 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 — 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) → 1.753 bpb (−11.9% vs xz, −15% vs Brotli, −24.5% vs bzip2)
alice29.txt → 2.119 bpb (−16.9% 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 — no mixer, no gradient descent, just counting.
The Tweedie denoising layer adds 2.3–2.7% on every file tested — 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.
💻 Code: https://github.com/robtacconelli/midicoth
📄 Paper: Micro-Diffusion Compression -- Binary Tree Tweedie Denoising for Online Probability Estimation (2603.08771)
⭐ Space: robtacconelli/midicoth
If you ever wondered whether diffusion ideas belong in data compression — here's proof they do. ⭐ appreciated!
robtacconelli
authored a
paper 6 months ago
robtacconelli
submitted a
paper to Daily Papers 6 months ago
robtacconelli
posted an update 7 months ago
Post
3650
🏆 Nacrith: a 135M model that out-compresses everything on natural language
What if a tiny LM could compress english text better than _every_ compressor out there — classical or neural, small or large?
Nacrith pairs SmolLM2-135M with an ensemble of online predictors and high-precision arithmetic coding.
What's inside
The standard LLM+arithmetic coding approach wastes ~75% of CDF precision on large vocabularies. Our CDF-24 fix alone recovers 0.5 bpb. On top: a token N-gram that skips the GPU on predictable tokens, an adaptive bias head, llama.cpp backend (7× faster than PyTorch), multi-GPU parallel compression, and a binary file format (NC06) — the first LLM-based binary compressor we know of.
Runs on a GTX 1050 Ti. ~500 MB weights, ~1.2 GB VRAM per worker.
💻 Code: https://github.com/robtacconelli/Nacrith-GPU
⭐ Space: robtacconelli/Nacrith-GPU
📄 Paper: Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding (2602.19626)
Try it, break it, share your results — all feedback welcome. ⭐ on the repo appreciated!
Results across all systems we tested:
- alice29.txt → 0.918 bpb (−44% vs CMIX, −20% vs ts_zip) — below the 2nd-order Shannon entropy bound
- enwik8 (100 MB) → 0.9389 bpb (−8% vs FineZip/LLMZip's 8B model, −15% vs ts_zip)
- Unseen text → 0.723 bpb on a doc published after training cutoff — no memorization, 26% better than FineZip/LLMZip on the same model
SmolLM2-135M by
HuggingFaceTB
What if a tiny LM could compress english text better than _every_ compressor out there — classical or neural, small or large?
Nacrith pairs SmolLM2-135M with an ensemble of online predictors and high-precision arithmetic coding.
What's inside
The standard LLM+arithmetic coding approach wastes ~75% of CDF precision on large vocabularies. Our CDF-24 fix alone recovers 0.5 bpb. On top: a token N-gram that skips the GPU on predictable tokens, an adaptive bias head, llama.cpp backend (7× faster than PyTorch), multi-GPU parallel compression, and a binary file format (NC06) — the first LLM-based binary compressor we know of.
Runs on a GTX 1050 Ti. ~500 MB weights, ~1.2 GB VRAM per worker.
💻 Code: https://github.com/robtacconelli/Nacrith-GPU
⭐ Space: robtacconelli/Nacrith-GPU
📄 Paper: Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding (2602.19626)
Try it, break it, share your results — all feedback welcome. ⭐ on the repo appreciated!
Results across all systems we tested:
- alice29.txt → 0.918 bpb (−44% vs CMIX, −20% vs ts_zip) — below the 2nd-order Shannon entropy bound
- enwik8 (100 MB) → 0.9389 bpb (−8% vs FineZip/LLMZip's 8B model, −15% vs ts_zip)
- Unseen text → 0.723 bpb on a doc published after training cutoff — no memorization, 26% better than FineZip/LLMZip on the same model
SmolLM2-135M by
- 1 reply
robtacconelli
submitted a
paper to Daily Papers 7 months ago