Compressive algorithmic randomness: Gibbs-randomness proposition for massively energy efficient deep learning

Figure: Dual Tomographic Compression
Performance, Süzen, 2025.

Preamble

Randomness is elusive and its probably one of the outstanding concepts for human scientific endeavour, along with gravity. Kolmogorov complexity, appears to be so novel in trying to answering "what is randomness?". The idea that the length of the smallest model that can generate the random sequence determines its complexity was a turning point in history of science. Similarly, it implies choosing the simplest model for explaining a phenomenon. That's why Kolmogorov's work was also supported by the ideas of Solomonoff and Chaitin. A recent work, explores this algorithmic information from compression perspective with Gibbs entropy.

A strange tale of path from applied research to fundamental proposition. 

During study of model compression algorithm development, I have noticed an amazing behaviour that information, entropy and compression over compression process have a more in depth. 

New concepts in compression and randomness via train-compress cycles

Here, we explain the new concepts for both deep learning model compression and on the interplay between compression and algorithmic randomness.

Inverse compressed sensing (iCS): Normally CS procedure is applied to reconstruct an unknown signal with fewer measurements. In the case of deep learning train-compress, weights are known at one point in the training cycle. If we create hypothetical measurements, using CS formulations, we can reconstruct weights sparse projection. 

Dual Tomographic Compression: Applying iCS for the input and output of neuronal level, layer-wise, simultaneously.  

Weight rays:  An output reconstructed vector out of DTC; weights given sparsity level, though they are not generated in isolation but within train-compress cycle.

Gibbs randomness proposition : An extension of Kolmogorov complexity for a compression process. That, directed randomness is the same as complexity reduction, i.e., compression. 

Conclusion 

A new technique called DTC can be used to train deep learning with model compression on the fly. This gives rise to massively energy efficient deep learning, reaching almost ~98% reduction in energy use.  Moreover, the technique also demonstrated an extended version of Kolmogorov complexity. 

Further reading 

Paper & codes are released :

• Paper: Gibbs randomness-compression proposition: An efficient deep learning 
  arXiv:2505.23869 (2025)
• Codes: https://github.com/msuzen/research/tree/main/gibbs-randomness-compression 

Cite as 

 @misc{suzen25car, 

     title = {Compressive algorithmic randomness: <br>Gibbs-randomness proposition for massively energy efficient deep learning}, 

     howpublished = {\url{ https://science-memo.blogspot.com/2025/06/compressive-algorithmic-randomness.html}}, 

     author = {Mehmet Süzen},

     year = {2025}

}  

Mathematical Definition of Heuristic Causal Inference: What differentiates DAGs and do-calculus?

Preamble 

David Hume (Wikipedia)

Experimental design is not a new concept and randomised control trials (RCTs) are our solid gold standard of doing quantitative research, when no apparent physical laws are available to validate observations.  However, it is very expensive to design RCTs, not ethical or either not possible due to logistical reasons in some cases. Then we fall into Causal Inference's heuristic frameworks, such as potential outcomes, matching, and time-series interventions in imagining counterfactuals and interventions. These methods provide immensely successful toolbox for quantitative scientist where by systems do not have any known physical laws. DAGs and do-calculus, differentiates from all these approaches that try to move away from full heuristics. In this post we try to postulate this formally in mathematical terms in the context of causal inference over observational data framework. We established that DAGs and do-calculus bring  mathematically more principled way of practicing causal inference akin to theoretical physics attitude. 

Definition of Heuristic Causal Inference (HeuristicCI) : Observational Data 

Heuristics in general implies an algorithmic approximate solution, usually appear as numerical and statistical algorithms in causal inference whereby full RCT is not available. This can be formalised as follows, 

Definition (HeuristicCI) Given dataset of  $n-$dimensions $\mathscr{D} \in \mathbb{R}^{n}$ observation, having variates of $X=x_{i}$, with each having different sub-sets (categories within $x_{i}$), having at least one category of observations.  We want to test  causal connection between two distinct subsets of $X$,  $\mathscr{S}_{1} , \mathscr{S}_{2}$, given an interventional versions or imagined counterfactual where by at least one of the subset is available,  $\mathscr{S}_{1}^{int} , \mathscr{S}_{2}^{int}$. Using an algorithm $\mathscr{A}$ that processes dataset to test an effect size $\delta$ using a statistic $\beta$,  as follows, $$ \delta= \beta(\mathscr{S}_{1} , \mathscr{S}_{1}^{int})-\beta(\mathscr{S}_{2} , \mathscr{S}_{2}^{int})$$ statistic $\beta$ can be result of a machine learning procedure as well and difference in $\delta$ is only a particular choice, i.e., such as Average Treatment Effect (ATE). The algorithm  $\mathscr{A}$ is called  HeuristicCI.

Many of the non-DAGs and do-calculus methods directly falls into this category, such as potential outcomes, uplift, matching and synthetic controls.  This definition could be quite obvious to practitioners that has a good handle in mathematical definitions. Moreover, HeuristicCI  implies solely data-driven approach to causality inline with Hume's pure-empirical view-point. 

Primary distinction in practicing DAGs that it brings causal ordering naturally [suezen23pco] with scientist's cognitive process encoded, where by HeuristicCI search for statistical effect size that has a causal component in fully data-driven way. However, a HybridCI would entails using DAGs and do-calculus in connection with data driven approaches.

Conclusion

In this short exposition, we introduced HeuristicCI  concept that category of methods that do not use DAGs and do-calculus explicitly in causal inference practice. However, we do not put a well designed RCTs  in this category. Because, as a gold standard approach whereby properly encoded experimental design generates full interventional data reflecting scientist's domain knowledge. 

References and Further reading

• Looper repo : A resource list for causality in statistics, data science and physics
• [suezen23pco] Practical Causal Ordering: Why weighted DAGs are powerful for causal inference?
• Related Wikipedia articles 
• Propensity score matching 
• Synthetic control method
• Difference in Differences
• Uplift Modelling

Please cite as follows:

 @misc{suezen23hci, 

     title = {Mathematical Definition of Heuristic Causal Inference: What differantiates DAGs and do-calculus?}, 

     howpublished = {\url{https://science-memo.blogspot.com/2023/11/heuristic-causal-inference.html}, 

     author = {Mehmet Süzen},

     year = {2023}

}  

Postscript A: Why Pearlian Causal Inference is very significant progress for empirical science? 

Judea Pearl's framework for causality sometimes referred to as “mathematisation of causality”. However, “axiomatic foundations of causal inference” is fair identification, Pearl's contribution to the field is in par with Kolmogorov's axiomatic foundations of probability. Key papers of this axiomatic foundations are published in 1993 (back-doors) [1] and 1995 (do-calculus) [2].  

Original works of Axiomatic foundation for causal inference:

[1] Pearl, J., “Graphical models, causality, and intervention,” Statistical Science, Vol. 8, pp. 266–269, 1993. 

[2] Pearl, J., “Causal diagrams for empirical research,” Biometrika, Vol. 82, Num. 4, pp. 669–710, 1995. 

Freeman Dyson's contribution to deep learning: Circular ensembles mimics trained deep neural networks

In memory of Professor Dyson, also see the paper Equivalence in Deep Neural Networks via Conjugate Matrix Ensembles

Preamble 

Dyson 2007 (Wikipedia) 

Freeman Dyson was a polymath scientist: theoretical physicist, mathematician and visionary thinker among others. In this post, we will briefly summarise his contribution to deep learning,  i.e., deep neural networks.  Obscure usage of his circular ensembles as a simulation tool in conjunction with the concept of ergodicity explained why deep learning systems learn in such high accuracy.

A simulation tool for deep learning: Circular (Random Matrix) Ensembles

Circular ensembles [1,2,3] developed by Dyson in 1962 for explaining quantum statistical mechanics systems as a modification of basic random matrix theory. Circular ensembles can be used in simulating deep learning architectures [4]. Basically, his three ensembles can be used to generate a "trained deep neural network". It is shown by myself with colleagues from Hamburg and Mallorca that using Dyson's ensembles generated networks, deeper they are so-called spectral ergodicity goes down [4], this is recently proved on real networks as well [5].

How to generate a simulated trained deep neural network in Python

Using Bristol python package [6] one could generate a set of weight matrices corresponding to each layer connections, i.e., weight matrices. A simple example, using Circular Unitary Ensemble (CUE), let's say we have 4 hidden layers of  64, 64, 128, 256 units. This would generate learned weight matrices of sizes 64x64, 64x128 and 128x256, One possible trained network weights can be generated: Note that we make non-square ones by simple multiplying by its transpose. 

from bristol.ensembles import circular
ce = circular()
seed_v   = 997123
W1 = ce.gue(64, set_seed=True, seed=seed_v)
W2 = ce.gue(128, set_seed=True, seed=seed_v)
W3 = ce.gue(256, set_seed=True, seed=seed_v)

These are complex matrices, one could take the arguments or use them as it is if only eigenvalues are needed.  An example of a trained network generation can be found in Zenedo. One can use any one of the circular ensembles.

Conclusion

Dyson's contributions are so bright that even his mathematical tools appear in modern deep learning research. He will be remembered many generations to come as a bright scientist and a polymath. 

References 

[1] Freeman Dyson, Journal of Mathematical Physics 3, 1199 (1962) [link]
[2] Michael Berry, New Journal of Physics 15 (2013) 013026 [link]
[3] Mehmet Süzen (2017), Summary Notebook on Circular ensembles [link]
[4] Spectral Ergodicity in Deep Learning Architectures via Surrogate Random Matrices,
Mehmet Süzen, Cornelius Weber, Joan J. Cerdà, arXiv:1704.08693 [link]
[5] Periodic Spectral Ergodicity: A Complexity Measure for Deep Neural Networks and Neural Architecture Search,
 Mehmet Süzen, Cornelius Weber, Joan J. Cerdà, arXiv:1911.07831 [link]
[6] Bristol Python package [link]

Compressed Sensing with R

Compressed sensing (CS) is pretty much appealing all current signal processing research community. At the same time, popularity of R language gaining a strong foot in the research and industry. Even though historically MATLAB is a de-facto standard in signal processing community, R is becoming a serious alternative to this. For example, the quality of R in time-series analysis or medical imaging is now an accepted fact. 

Last year, I have demonstrated how one can use R in compressed sensing research in a short tutorial in the pub, close to Liverpool street in London.  The package R1magic is available in CRAN. Package provides basic interface to perform 1-D compressed sensing with l1, TV penalized minimization. There are other packages doing similar regularized minimization. However the interface of R1magic is particularly designed for CS i.e. appearance of sparse bases in the objective function.  

Here is one simple example ( Version 0.1):

library(R1magic)#  Signal components
N <- 100
# Sparse components
K <- 4 
#  Up to Measurements  > K LOG (N/K)
M <- 40
# Measurement Matrix (Random Sampling Sampling)
phi <- GaussianMatrix(N,M)
# R1magic generate random signal
xorg <- sparseSignal(N, K, nlev=1e-3)
y <- phi %*% xorg ;# generate measurement
T <- diag(N) ;# Do identity transform
p <- matrix(0, N, 1) ;# initial guess
# R1magic Convex Minimization ! (unoptimized-parameter)
ll <- solveL1(phi, y, T, p)
x1 <- ll$estimate
plot( 1:100, seq(0.011,1.1,0.011), type = "n",xlab="",ylab="")
title(main="Random Sparse Signal Recovery",
      xlab="Signal Component",ylab="Spike Value")
lines(1:100, xorg , col = "red")
lines(1:100, x1, col = "blue", cex = 1.5) 
# shifted by 5 for clearity

Blue line is the reconstructed signal with R1magic.

Optimal random search

A recent work shows how to exploit a priori distribution in random search.It is shown that square of the distribution must be selected as a search distribution [pre][arxiv].