6 citations · 26 across the 32 of their papers we have counts for
37 papers
Learning Finite-Memory Binary Sources
Maciej Skorski
Estimating biased finite-memory sources from a single trajectory is a fundamental problem with practical impact, for example in estimating entropy for cryptography. We study order-…
Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding
Maciej Skorski, Alina Landowska
How do Large Language Models understand moral dimensions compared to humans? This first large-scale Bayesian evaluation of market-leading language models provides the answer. In co…
Mapping Technological Futures: Anticipatory Discourse Through Text Mining
Maciej Skorski, Alina Landowska, Krzysztof Rajda
The volatility and unpredictability of emerging technologies, such as artificial intelligence (AI), generate significant uncertainty, which is widely discussed on social media. Thi…
What Twitter Data Tell Us about the Future?
Alina Landowska, Marek Robak, Maciej Skorski
Anticipation is a fundamental human cognitive ability that involves thinking about and living towards the future. While language markers reflect anticipatory thinking, research on…
Exact Non-Oblivious Performance of Rademacher Random Embeddings
Maciej Skorski, Alessandro Temperoni
This paper revisits the performance of Rademacher random projections, establishing novel statistical guarantees that are numerically sharp and non-oblivious with respect to the inp…
Tight Chernoff-Like Bounds Under Limited Independence
Maciej Skorski
This paper develops sharp bounds on moments of sums of k-wise independent bounded random variables, under constrained average variance. The result closes the problem addressed in p…
Robust and Provable Guarantees for Sparse Random Embeddings
Maciej Skorski, Alessandro Temperoni, Martin Theobald
In this work, we improve upon the guarantees for sparse random embeddings, as they were recently provided and analyzed by Freksen at al. (NIPS'18) and Jagadeesan (NIPS'19). Specifi…
Mean-Squared Accuracy of Good-Turing Estimator
Maciej Skorski
The brilliant method due to Good and Turing allows for estimating objects not occurring in a sample. The problem, known under names "sample coverage" or "missing mass" goes back to…
On Missing Mass Variance
Maciej Skorski
The missing mass refers to the probability of elements not observed in a sample, and since the work of Good and Turing during WWII, has been studied extensively in many areas inclu…
Confidence-Optimal Random Embeddings
Maciej Skorski
The seminal result of Johnson and Lindenstrauss on random embeddings has been intensively studied in applied and theoretical computer science. Despite that vast body of literature,…
Bernstein-Type Bounds for Beta Distribution
Maciej Skorski
This work obtains sharp closed-form exponential concentration inequalities of Bernstein type for the ubiquitous beta distribution, improving upon sub-gaussian and sub-gamma bounds…
Random Embeddings with Optimal Accuracy
Maciej Skorski
This work constructs Jonson-Lindenstrauss embeddings with best accuracy, as measured by variance, mean-squared error and exponential concentration of the length distortion. Lower b…
A Modern Analysis of Hutchinson's Trace Estimator
Maciej Skorski
The paper establishes the new state-of-art in the accuracy analysis of Hutchinson's trace estimator. Leveraging tools that have not been previously used in this context, particular…
Handy Formulas for Binomial Moments
Maciej Skorski
Despite the relevance of the binomial distribution for probability theory and applied statistical inference, its higher-order moments are poorly understood. The existing formulas a…
Simple Analysis of Johnson-Lindenstrauss Transform under Neuroscience Constraints
Maciej Skorski
The paper re-analyzes a version of the celebrated Johnson-Lindenstrauss Lemma, in which matrices are subjected to constraints that naturally emerge from neuroscience applications:…
Concentration Bounds for the Collision Estimator
Maciej Skorski
We prove a strong concentration result about the natural collision estimator, which counts the number of collisions that occur within an iid sample. This estimator is at the heart…
Revisiting Concentration of Missing Mass
Maciej Skorski
We revisit the problem of \emph{missing mass concentration}, developing a new method of estimating concentration of heterogenic sums, in spirit of celebrated Rosenthal's inequality…
Efficient Sampled Softmax for Tensorflow
Maciej Skorski
This short paper discusses an efficient implementation of \emph{sampled softmax loss} for Tensorflow. The speedup over the default implementation is achieved due to simplification…
Revisiting Initialization of Neural Networks
Maciej Skorski, Alessandro Temperoni, Martin Theobald
The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balanc…
Practical Estimation of Renyi Entropy
Maciej Skorski
Entropy Estimation is an important problem with many applications in cryptography, statistic,machine learning. Although the estimators optimal with respect to the sample complexity…
Missing Mass Concentration for Markov Chains
Maciej Skorski
The problem of missing mass in statistical inference (posed by McAllester and Ortiz, NIPS'02; most recently revisited by Changa and Thangaraj, ISIT'2019) seeks to estimate the weig…
Chain Rules for Hessian and Higher Derivatives Made Easy by Tensor Calculus
Maciej Skorski
Computing multivariate derivatives of matrix-like expressions in the compact, coordinate free fashion is very important for both theory and applied computations (e.g. optimization…
Bounds on Bayes Factors for Binomial A/B Testing
Maciej Skorski
Bayes factors, in many cases, have been proven to bridge the classic -value based significance testing and bayesian analysis of posterior odds. This paper discusses this phenomena…
Kernel Density Estimation Bias under Minimal Assumptions
Maciej Skorski
Kernel Density Estimation is a very popular technique of approximating a density function from samples. The accuracy is generally well-understood and depends, roughly speaking, on…