šŸŽ“How I Study AIHISA
šŸ“–Read
šŸ“„PapersšŸ“°BlogsšŸŽ¬Courses
šŸ’”Learn
šŸ›¤ļøPathsšŸ“šTopicsšŸ’”ConceptsšŸŽ“Shorts
šŸŽÆPractice
šŸ“Daily LogšŸŽÆPromptsšŸ§ Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Concepts6

Groups

šŸ“Linear Algebra15šŸ“ˆCalculus & Differentiation10šŸŽÆOptimization14šŸŽ²Probability Theory12šŸ“ŠStatistics for ML9šŸ“”Information Theory10šŸ”ŗConvex Optimization7šŸ”¢Numerical Methods6šŸ•øGraph Theory for Deep Learning6šŸ”µTopology for ML5šŸŒDifferential Geometry6āˆžMeasure Theory & Functional Analysis6šŸŽ°Random Matrix Theory5šŸŒŠFourier Analysis & Signal Processing9šŸŽ°Sampling & Monte Carlo Methods10šŸ§ Deep Learning Theory12šŸ›”ļøRegularization Theory11šŸ‘ļøAttention & Transformer Theory10šŸŽØGenerative Model Theory11šŸ”®Representation Learning10šŸŽ®Reinforcement Learning Mathematics9šŸ”„Variational Methods8šŸ“‰Loss Functions & Objectives10ā±ļøSequence & Temporal Models8šŸ’ŽGeometric Deep Learning8

Category

šŸ”·Allāˆ‘Mathāš™ļøAlgošŸ—‚ļøDSšŸ“šTheory

Level

AllBeginnerIntermediate
āš™ļøAlgorithmIntermediate

Efficient Attention Mechanisms

Standard softmax attention costs O(nĀ²) in sequence length because every token compares with every other token.

#linear attention#efficient attention#kernel trick+12
āš™ļøAlgorithmIntermediate

Debugging Strategies for CP

Systematic debugging beats guesswork: always re-read the statement, re-check constraints, and verify the output format before touching code.

#competitive programming
Advanced
Filtering by:
#prefix sums
#debugging
#stress testing
+12
āš™ļøAlgorithmIntermediate

Fast I/O and Optimization Tricks

Fast I/O reduces overhead from C and C++ stream synchronization and avoids unnecessary flushes, which can cut runtime by multiples on large inputs.

#fast io#iostream synchronization#cin.tie+12
āš™ļøAlgorithmAdvanced

Divide and Conquer DP Optimization

Divide and Conquer DP optimization speeds up DP transitions of the form dp[i][j] = min over k of dp[i-1][k] + C(k, j) when the optimal k is monotone in j.

#divide and conquer dp#monge array#quadrangle inequality+10
āš™ļøAlgorithmAdvanced

Knuth Optimization

Knuth Optimization speeds up a class of interval dynamic programming (DP) from O(n^3) to O(n^2) by exploiting the monotonicity of optimal split points.

#knuth optimization#interval dp#quadrangle inequality+12
āš™ļøAlgorithmIntermediate

Interval DP

Interval DP solves problems where the optimal answer for a segment [i, j] depends on answers of its subsegments.

#interval dp#matrix chain multiplication#burst balloons+12