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

Concepts7

Groups

šŸ“Linear Algebra15šŸ“ˆCalculus & Differentiation10šŸŽÆOptimization14šŸŽ²Probability Theory12šŸ“ŠStatistics for ML9šŸ“”Information Theory10šŸ”ŗConvex Optimization7šŸ”¢Numerical Methods6šŸ•øGraph Theory for Deep Learning6šŸ”µTopology for ML5🌐Differential Geometry6āˆžMeasure Theory & Functional Analysis6šŸŽ°Random Matrix Theory5🌊Fourier Analysis & Signal Processing9šŸŽ°Sampling & Monte Carlo Methods10🧠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(n²) 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
āˆ‘MathIntermediate

Harmonic Lemma

The Harmonic Lemma says that the values of \lfloor n/i \rfloor only change about 2\sqrt{n} times, so you can iterate those value blocks in O(\sqrt{n}) instead of O(n).

#harmonic lemma#integer division trick#block decomposition+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
šŸ—‚ļøData StructureIntermediate

Merge Sort Tree

A Merge Sort Tree is a segment tree where every node stores the sorted list of values in its segment.

#merge sort tree#segment tree#range query+12
šŸ—‚ļøData StructureIntermediate

Monotonic Deque

A monotonic deque is a double-ended queue that keeps elements in increasing or decreasing order so that the front always holds the current optimum (min or max).

#monotonic deque#sliding window maximum#sliding window minimum+12