Akshay Balsubramani
PulseAugur coverage of Akshay Balsubramani — every cluster mentioning Akshay Balsubramani across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New paper offers information-theoretic analysis of SGD methods
A new paper proposes an information-theoretic analysis of stochastic gradient descent (SGD) and its variants, offering an alternative to traditional geometric approaches. The research demonstrates that a preconditioned …
-
New paper explores information flow in martingales, unifying concentration inequalities
A new paper published on arXiv details advancements in understanding information flow within the path space of nonnegative martingales. The research introduces exact variational identities that apply even at arbitrary r…
-
New paper details Bayesian updating and regret in game theory
A new paper titled "The concentration game: Bayesian updating, regret, and information" by Akshay Balsubramani explores a two-player zero-sum repeated game. This game's value identity is designed to simultaneously gener…
-
New research details exact information accounting for Bayesian and multiplicative-weights updates
A new research paper introduces an exact information-accounting identity for Bayesian and multiplicative-weights updates. This identity reveals that the regret of any such update is directly related to the immediate pay…
-
New divergence family generalizes multi-distribution comparisons
A new paper introduces a novel family of divergences designed to generalize the comparison of two probability distributions to multiple distributions. These multi-distribution divergences, termed "multi-way coincidence …
-
New multi-distribution Rényi divergences characterized by researchers · 2 sources tracked
Researchers have characterized a new family of multi-distribution generalizations of Rényi divergences, which are crucial for comparing multiple probability distributions simultaneously. This new family, termed multi-wa…
-
New normalization method for sparse count data introduced
A new paper introduces a deviance-style normalization method for analyzing sparse, jointly overdispersed count matrices, particularly relevant for biochemical assays like sequencing. The proposed Dirichlet-multinomial (…
-
New algebraic identity unifies information theory results
A new paper introduces a unified algebraic identity that connects various information-theoretic variational results. This identity generalizes classical formulas for entropy and divergence to multiple priors and holds f…